Merge branch 'main' into fix/_should_force_answer

pyproject.toml

@@ -11,7 +11,7 @@ dependencies = [
     # Core Dependencies
     "pydantic>=2.4.2",
     "openai>=1.13.3",
-    "litellm>=1.44.22",
+    "litellm>=1.56.4",
     "instructor>=1.3.3",
     
     # Text Processing

src/crewai/agents/agent_builder/base_agent_executor_mixin.py

@@ -26,7 +26,7 @@ class CrewAgentExecutorMixin:
 
     def _should_force_answer(self) -> bool:
         """Determine if a forced answer is required based on iteration count."""
-        return (self.iterations >= self.max_iter) and not self.have_forced_answer
+        return self.iterations >= self.max_iter
 
     def _create_short_term_memory(self, output) -> None:
         """Create and save a short-term memory item if conditions are met."""

tests/agent_test.py

@@ -1457,7 +1457,7 @@ def test_agent_with_ollama_llama3():
     assert agent.llm.model == "ollama/llama3.2:3b"
     assert agent.llm.base_url == "http://localhost:11434"
 
-    task = "Respond in 20 words. Which model are you?"
+    task = "Respond in 20 words. Who are you?"
     response = agent.llm.call([{"role": "user", "content": task}])
 
     assert response
@@ -1473,9 +1473,7 @@ def test_llm_call_with_ollama_llama3():
         temperature=0.7,
         max_tokens=30,
     )
-    messages = [
+    messages = [{"role": "user", "content": "Respond in 20 words. Who are you?"}]
-        {"role": "user", "content": "Respond in 20 words. Which model are you?"}
-    ]
 
     response = llm.call(messages)
 

tests/cassettes/test_agent_execute_task_with_ollama.yaml

@@ -12,34 +12,862 @@ interactions:
       available and give your best Final Answer, your job depends on it!\n\nThought:\n\n",
       "options": {"stop": ["\nObservation:"]}, "stream": false}'
     headers:
-      Accept:
+      accept:
       - '*/*'
-      Accept-Encoding:
+      accept-encoding:
       - gzip, deflate
-      Connection:
+      connection:
       - keep-alive
-      Content-Length:
+      content-length:
       - '839'
-      Content-Type:
+      host:
-      - application/json
+      - localhost:11434
-      User-Agent:
+      user-agent:
-      - python-requests/2.32.3
+      - litellm/1.56.4
     method: POST
     uri: http://localhost:11434/api/generate
   response:
-    body:
+    content: '{"model":"llama3.2:3b","created_at":"2024-12-31T16:56:15.759718Z","response":"Final
-      string: '{"model":"llama3.2:3b","created_at":"2025-01-02T20:05:52.24992Z","response":"Final
+      Answer: Artificial Intelligence (AI) refers to the development of computer systems
-        Answer: Artificial Intelligence (AI) refers to the development of computer
+      able to perform tasks that typically require human intelligence, including learning,
-        systems capable of performing tasks that typically require human intelligence,
+      problem-solving, decision-making, and perception.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,744,512,2675,527,1296,3560,13,1296,93371,198,7927,4443,5915,374,25,1296,5915,198,1271,3041,856,1888,4686,1620,4320,311,279,3465,1005,279,4839,2768,3645,1473,85269,25,358,1457,649,3041,264,2294,4320,198,19918,22559,25,4718,1620,4320,2011,387,279,2294,323,279,1455,4686,439,3284,11,433,2011,387,15632,7633,382,40,28832,1005,1521,20447,11,856,2683,14117,389,433,2268,14711,2724,1473,5520,5546,25,83017,1148,15592,374,304,832,11914,271,2028,374,279,1755,13186,369,701,1620,4320,25,362,832,1355,18886,16540,315,15592,198,9514,28832,471,279,5150,4686,2262,439,279,1620,4320,11,539,264,12399,382,11382,0,1115,374,48174,3062,311,499,11,1005,279,7526,2561,323,3041,701,1888,13321,22559,11,701,2683,14117,389,433,2268,85269,1473,128009,128006,78191,128007,271,19918,22559,25,59294,22107,320,15836,8,19813,311,279,4500,315,6500,6067,3025,311,2804,9256,430,11383,1397,3823,11478,11,2737,6975,11,3575,99246,11,5597,28846,11,323,21063,13],"total_duration":1156303250,"load_duration":35999125,"prompt_eval_count":181,"prompt_eval_duration":408000000,"eval_count":38,"eval_duration":711000000}'
-        such as learning, problem-solving, decision-making, and perception.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,744,512,2675,527,1296,3560,13,1296,93371,198,7927,4443,5915,374,25,1296,5915,198,1271,3041,856,1888,4686,1620,4320,311,279,3465,1005,279,4839,2768,3645,1473,85269,25,358,1457,649,3041,264,2294,4320,198,19918,22559,25,4718,1620,4320,2011,387,279,2294,323,279,1455,4686,439,3284,11,433,2011,387,15632,7633,382,40,28832,1005,1521,20447,11,856,2683,14117,389,433,2268,14711,2724,1473,5520,5546,25,83017,1148,15592,374,304,832,11914,271,2028,374,279,1755,13186,369,701,1620,4320,25,362,832,1355,18886,16540,315,15592,198,9514,28832,471,279,5150,4686,2262,439,279,1620,4320,11,539,264,12399,382,11382,0,1115,374,48174,3062,311,499,11,1005,279,7526,2561,323,3041,701,1888,13321,22559,11,701,2683,14117,389,433,2268,85269,1473,128009,128006,78191,128007,271,19918,22559,25,59294,22107,320,15836,8,19813,311,279,4500,315,6500,6067,13171,315,16785,9256,430,11383,1397,3823,11478,11,1778,439,6975,11,3575,99246,11,5597,28846,11,323,21063,13],"total_duration":1461909875,"load_duration":39886208,"prompt_eval_count":181,"prompt_eval_duration":701000000,"eval_count":39,"eval_duration":719000000}'
     headers:
       Content-Length:
-      - '1537'
+      - '1528'
       Content-Type:
       - application/json; charset=utf-8
       Date:
-      - Thu, 02 Jan 2025 20:05:52 GMT
+      - Tue, 31 Dec 2024 16:56:15 GMT
-    status:
+    http_version: HTTP/1.1
-      code: 200
+    status_code: 200
-      message: OK
+- request:
+    body: '{"name": "llama3.2:3b"}'
+    headers:
+      accept:
+      - '*/*'
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '23'
+      content-type:
+      - application/json
+      host:
+      - localhost:11434
+      user-agent:
+      - litellm/1.56.4
+    method: POST
+    uri: http://localhost:11434/api/show
+  response:
+    content: "{\"license\":\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version
+      Release Date: September 25, 2024\\n\\n\u201CAgreement\u201D means the terms
+      and conditions for use, reproduction, distribution \\nand modification of the
+      Llama Materials set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications,
+      manuals and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
+      or \u201Cyou\u201D means you, or your employer or any other person or entity
+      (if you are \\nentering into this Agreement on such person or entity\u2019s
+      behalf), of the age required under\\napplicable laws, rules or regulations to
+      provide legal consent and that has legal authority\\nto bind your employer or
+      such other person or entity if you are entering in this Agreement\\non their
+      behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
+      and software and algorithms, including\\nmachine-learning model code, trained
+      model weights, inference-enabling code, training-enabling code,\\nfine-tuning
+      enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
+      Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
+      (and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
+      or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
+      or, \\nif you are an entity, your principal place of business is in the EEA
+      or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
+      EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
+      or distributing any portion or element of the Llama Materials,\\nyou agree to
+      be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
+      \   a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
+      and royalty-free limited license under Meta\u2019s intellectual property or
+      other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
+      distribute, copy, create derivative works \\nof, and make modifications to the
+      Llama Materials.  \\n\\n    b. Redistribution and Use.  \\n\\n        i. If
+      you distribute or make available the Llama Materials (or any derivative works
+      thereof), \\nor a product or service (including another AI model) that contains
+      any of them, you shall (A) provide\\na copy of this Agreement with any such
+      Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
+      a related website, user interface, blogpost, about page, or product documentation.
+      If you use the\\nLlama Materials or any outputs or results of the Llama Materials
+      to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
+      or made available, you shall also include \u201CLlama\u201D\\nat the beginning
+      of any such AI model name.\\n\\n        ii. If you receive Llama Materials,
+      or any derivative works thereof, from a Licensee as part\\nof an integrated
+      end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
+      \       iii. You must retain in all copies of the Llama Materials that you distribute
+      the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
+      as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
+      Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
+      \       iv. Your use of the Llama Materials must comply with applicable laws
+      and regulations\\n(including trade compliance laws and regulations) and adhere
+      to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
+      which is hereby \\nincorporated by reference into this Agreement.\\n  \\n2.
+      Additional Commercial Terms. If, on the Llama 3.2 version release date, the
+      monthly active users\\nof the products or services made available by or for
+      Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
+      active users in the preceding calendar month, you must request \\na license
+      from Meta, which Meta may grant to you in its sole discretion, and you are not
+      authorized to\\nexercise any of the rights under this Agreement unless or until
+      Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
+      UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
+      THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
+      ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
+      IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
+      MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
+      DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
+      AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
+      OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
+      ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
+      TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
+      \\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
+      EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
+      OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
+      \   a. No trademark licenses are granted under this Agreement, and in connection
+      with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
+      owned by or associated with the other or any of its affiliates, \\nexcept as
+      required for reasonable and customary use in describing and redistributing the
+      Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
+      you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
+      \\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
+      brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
+      All goodwill arising out of your use of the Mark \\nwill inure to the benefit
+      of Meta.\\n\\n    b. Subject to Meta\u2019s ownership of Llama Materials and
+      derivatives made by or for Meta, with respect to any\\n    derivative works
+      and modifications of the Llama Materials that are made by you, as between you
+      and Meta,\\n    you are and will be the owner of such derivative works and modifications.\\n\\n
+      \   c. If you institute litigation or other proceedings against Meta or any
+      entity (including a cross-claim or\\n    counterclaim in a lawsuit) alleging
+      that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
+      \   of any of the foregoing, constitutes infringement of intellectual property
+      or other rights owned or licensable\\n    by you, then any licenses granted
+      to you under this Agreement shall terminate as of the date such litigation or\\n
+      \   claim is filed or instituted. You will indemnify and hold harmless Meta
+      from and against any claim by any third\\n    party arising out of or related
+      to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
+      The term of this Agreement will commence upon your acceptance of this Agreement
+      or access\\nto the Llama Materials and will continue in full force and effect
+      until terminated in accordance with the terms\\nand conditions herein. Meta
+      may terminate this Agreement if you are in breach of any term or condition of
+      this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
+      use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
+      of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
+      be governed and construed under the laws of the State of \\nCalifornia without
+      regard to choice of law principles, and the UN Convention on Contracts for the
+      International\\nSale of Goods does not apply to this Agreement. The courts of
+      California shall have exclusive jurisdiction of\\nany dispute arising out of
+      this Agreement.\\n**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta is committed
+      to promoting safe and fair use of its tools and features, including Llama 3.2.
+      If you access or use Llama 3.2, you agree to this Acceptable Use Policy (\u201C**Policy**\u201D).
+      The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
+      Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
+      you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
+      the law or others\u2019 rights, including to:\\n    1. Engage in, promote, generate,
+      contribute to, encourage, plan, incite, or further illegal or unlawful activity
+      or content, such as:\\n        1. Violence or terrorism\\n        2. Exploitation
+      or harm to children, including the solicitation, creation, acquisition, or dissemination
+      of child exploitative content or failure to report Child Sexual Abuse Material\\n
+      \       3. Human trafficking, exploitation, and sexual violence\\n        4.
+      The illegal distribution of information or materials to minors, including obscene
+      materials, or failure to employ legally required age-gating in connection with
+      such information or materials.\\n        5. Sexual solicitation\\n        6.
+      Any other criminal activity\\n    1. Engage in, promote, incite, or facilitate
+      the harassment, abuse, threatening, or bullying of individuals or groups of
+      individuals\\n    2. Engage in, promote, incite, or facilitate discrimination
+      or other unlawful or harmful conduct in the provision of employment, employment
+      benefits, credit, housing, other economic benefits, or other essential goods
+      and services\\n    3. Engage in the unauthorized or unlicensed practice of any
+      profession including, but not limited to, financial, legal, medical/health,
+      or related professional practices\\n    4. Collect, process, disclose, generate,
+      or infer private or sensitive information about individuals, including information
+      about individuals\u2019 identity, health, or demographic information, unless
+      you have obtained the right to do so in accordance with applicable law\\n    5.
+      Engage in or facilitate any action or generate any content that infringes, misappropriates,
+      or otherwise violates any third-party rights, including the outputs or results
+      of any products or services using the Llama Materials\\n    6. Create, generate,
+      or facilitate the creation of malicious code, malware, computer viruses or do
+      anything else that could disable, overburden, interfere with or impair the proper
+      working, integrity, operation or appearance of a website or computer system\\n
+      \   7. Engage in any action, or facilitate any action, to intentionally circumvent
+      or remove usage restrictions or other safety measures, or to enable functionality
+      disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
+      planning or development of activities that present a risk of death or bodily
+      harm to individuals, including use of Llama 3.2 related to the following:\\n
+      \   8. Military, warfare, nuclear industries or applications, espionage, use
+      for materials or activities that are subject to the International Traffic Arms
+      Regulations (ITAR) maintained by the United States Department of State or to
+      the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
+      Convention Implementation Act of 1997\\n    9. Guns and illegal weapons (including
+      weapon development)\\n    10. Illegal drugs and regulated/controlled substances\\n
+      \   11. Operation of critical infrastructure, transportation technologies, or
+      heavy machinery\\n    12. Self-harm or harm to others, including suicide, cutting,
+      and eating disorders\\n    13. Any content intended to incite or promote violence,
+      abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
+      deceive or mislead others, including use of Llama 3.2 related to the following:\\n
+      \   14. Generating, promoting, or furthering fraud or the creation or promotion
+      of disinformation\\n    15. Generating, promoting, or furthering defamatory
+      content, including the creation of defamatory statements, images, or other content\\n
+      \   16. Generating, promoting, or further distributing spam\\n    17. Impersonating
+      another individual without consent, authorization, or legal right\\n    18.
+      Representing that the use of Llama 3.2 or outputs are human-generated\\n    19.
+      Generating or facilitating false online engagement, including fake reviews and
+      other means of fake online engagement\\n4. Fail to appropriately disclose to
+      end users any known dangers of your AI system\\n5. Interact with third party
+      tools, models, or software designed to generate unlawful content or engage in
+      unlawful or harmful conduct and/or represent that the outputs of such tools,
+      models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
+      to any multimodal models included in Llama 3.2, the rights granted under Section
+      1(a) of the Llama 3.2 Community License Agreement are not being granted to you
+      if you are an individual domiciled in, or a company with a principal place of
+      business in, the European Union. This restriction does not apply to end users
+      of a product or service that incorporates any such multimodal models.\\n\\nPlease
+      report any violation of this Policy, software \u201Cbug,\u201D or other problems
+      that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
+      Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
+      Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
+      Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
+      Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
+      3.2: LlamaUseReport@meta.com\",\"modelfile\":\"# Modelfile generated by \\\"ollama
+      show\\\"\\n# To build a new Modelfile based on this, replace FROM with:\\n#
+      FROM llama3.2:3b\\n\\nFROM /Users/brandonhancock/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff\\nTEMPLATE
+      \\\"\\\"\\\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
+      Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
+      if .Tools }}When you receive a tool call response, use the output to format
+      an answer to the orginal user question.\\n\\nYou are a helpful assistant with
+      tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
+      $_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
+      if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
+      if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
+      a JSON for a function call with its proper arguments that best answers the given
+      prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
+      dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
+      $.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
+      else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
+      end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
+      if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
+      }}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
+      .Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
+      else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
+      .Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
+      end }}\\n{{- end }}\\n{{- end }}\\\"\\\"\\\"\\nPARAMETER stop \\u003c|start_header_id|\\u003e\\nPARAMETER
+      stop \\u003c|end_header_id|\\u003e\\nPARAMETER stop \\u003c|eot_id|\\u003e\\nLICENSE
+      \\\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version Release Date:
+      September 25, 2024\\n\\n\u201CAgreement\u201D means the terms and conditions
+      for use, reproduction, distribution \\nand modification of the Llama Materials
+      set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications, manuals
+      and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
+      or \u201Cyou\u201D means you, or your employer or any other person or entity
+      (if you are \\nentering into this Agreement on such person or entity\u2019s
+      behalf), of the age required under\\napplicable laws, rules or regulations to
+      provide legal consent and that has legal authority\\nto bind your employer or
+      such other person or entity if you are entering in this Agreement\\non their
+      behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
+      and software and algorithms, including\\nmachine-learning model code, trained
+      model weights, inference-enabling code, training-enabling code,\\nfine-tuning
+      enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
+      Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
+      (and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
+      or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
+      or, \\nif you are an entity, your principal place of business is in the EEA
+      or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
+      EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
+      or distributing any portion or element of the Llama Materials,\\nyou agree to
+      be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
+      \   a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
+      and royalty-free limited license under Meta\u2019s intellectual property or
+      other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
+      distribute, copy, create derivative works \\nof, and make modifications to the
+      Llama Materials.  \\n\\n    b. Redistribution and Use.  \\n\\n        i. If
+      you distribute or make available the Llama Materials (or any derivative works
+      thereof), \\nor a product or service (including another AI model) that contains
+      any of them, you shall (A) provide\\na copy of this Agreement with any such
+      Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
+      a related website, user interface, blogpost, about page, or product documentation.
+      If you use the\\nLlama Materials or any outputs or results of the Llama Materials
+      to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
+      or made available, you shall also include \u201CLlama\u201D\\nat the beginning
+      of any such AI model name.\\n\\n        ii. If you receive Llama Materials,
+      or any derivative works thereof, from a Licensee as part\\nof an integrated
+      end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
+      \       iii. You must retain in all copies of the Llama Materials that you distribute
+      the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
+      as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
+      Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
+      \       iv. Your use of the Llama Materials must comply with applicable laws
+      and regulations\\n(including trade compliance laws and regulations) and adhere
+      to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
+      which is hereby \\nincorporated by reference into this Agreement.\\n  \\n2.
+      Additional Commercial Terms. If, on the Llama 3.2 version release date, the
+      monthly active users\\nof the products or services made available by or for
+      Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
+      active users in the preceding calendar month, you must request \\na license
+      from Meta, which Meta may grant to you in its sole discretion, and you are not
+      authorized to\\nexercise any of the rights under this Agreement unless or until
+      Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
+      UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
+      THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
+      ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
+      IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
+      MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
+      DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
+      AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
+      OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
+      ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
+      TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
+      \\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
+      EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
+      OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
+      \   a. No trademark licenses are granted under this Agreement, and in connection
+      with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
+      owned by or associated with the other or any of its affiliates, \\nexcept as
+      required for reasonable and customary use in describing and redistributing the
+      Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
+      you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
+      \\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
+      brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
+      All goodwill arising out of your use of the Mark \\nwill inure to the benefit
+      of Meta.\\n\\n    b. Subject to Meta\u2019s ownership of Llama Materials and
+      derivatives made by or for Meta, with respect to any\\n    derivative works
+      and modifications of the Llama Materials that are made by you, as between you
+      and Meta,\\n    you are and will be the owner of such derivative works and modifications.\\n\\n
+      \   c. If you institute litigation or other proceedings against Meta or any
+      entity (including a cross-claim or\\n    counterclaim in a lawsuit) alleging
+      that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
+      \   of any of the foregoing, constitutes infringement of intellectual property
+      or other rights owned or licensable\\n    by you, then any licenses granted
+      to you under this Agreement shall terminate as of the date such litigation or\\n
+      \   claim is filed or instituted. You will indemnify and hold harmless Meta
+      from and against any claim by any third\\n    party arising out of or related
+      to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
+      The term of this Agreement will commence upon your acceptance of this Agreement
+      or access\\nto the Llama Materials and will continue in full force and effect
+      until terminated in accordance with the terms\\nand conditions herein. Meta
+      may terminate this Agreement if you are in breach of any term or condition of
+      this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
+      use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
+      of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
+      be governed and construed under the laws of the State of \\nCalifornia without
+      regard to choice of law principles, and the UN Convention on Contracts for the
+      International\\nSale of Goods does not apply to this Agreement. The courts of
+      California shall have exclusive jurisdiction of\\nany dispute arising out of
+      this Agreement.\\\"\\nLICENSE \\\"**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta
+      is committed to promoting safe and fair use of its tools and features, including
+      Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use
+      Policy (\u201C**Policy**\u201D). The most recent copy of this policy can be
+      found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
+      Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
+      you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
+      the law or others\u2019 rights, including to:\\n    1. Engage in, promote, generate,
+      contribute to, encourage, plan, incite, or further illegal or unlawful activity
+      or content, such as:\\n        1. Violence or terrorism\\n        2. Exploitation
+      or harm to children, including the solicitation, creation, acquisition, or dissemination
+      of child exploitative content or failure to report Child Sexual Abuse Material\\n
+      \       3. Human trafficking, exploitation, and sexual violence\\n        4.
+      The illegal distribution of information or materials to minors, including obscene
+      materials, or failure to employ legally required age-gating in connection with
+      such information or materials.\\n        5. Sexual solicitation\\n        6.
+      Any other criminal activity\\n    1. Engage in, promote, incite, or facilitate
+      the harassment, abuse, threatening, or bullying of individuals or groups of
+      individuals\\n    2. Engage in, promote, incite, or facilitate discrimination
+      or other unlawful or harmful conduct in the provision of employment, employment
+      benefits, credit, housing, other economic benefits, or other essential goods
+      and services\\n    3. Engage in the unauthorized or unlicensed practice of any
+      profession including, but not limited to, financial, legal, medical/health,
+      or related professional practices\\n    4. Collect, process, disclose, generate,
+      or infer private or sensitive information about individuals, including information
+      about individuals\u2019 identity, health, or demographic information, unless
+      you have obtained the right to do so in accordance with applicable law\\n    5.
+      Engage in or facilitate any action or generate any content that infringes, misappropriates,
+      or otherwise violates any third-party rights, including the outputs or results
+      of any products or services using the Llama Materials\\n    6. Create, generate,
+      or facilitate the creation of malicious code, malware, computer viruses or do
+      anything else that could disable, overburden, interfere with or impair the proper
+      working, integrity, operation or appearance of a website or computer system\\n
+      \   7. Engage in any action, or facilitate any action, to intentionally circumvent
+      or remove usage restrictions or other safety measures, or to enable functionality
+      disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
+      planning or development of activities that present a risk of death or bodily
+      harm to individuals, including use of Llama 3.2 related to the following:\\n
+      \   8. Military, warfare, nuclear industries or applications, espionage, use
+      for materials or activities that are subject to the International Traffic Arms
+      Regulations (ITAR) maintained by the United States Department of State or to
+      the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
+      Convention Implementation Act of 1997\\n    9. Guns and illegal weapons (including
+      weapon development)\\n    10. Illegal drugs and regulated/controlled substances\\n
+      \   11. Operation of critical infrastructure, transportation technologies, or
+      heavy machinery\\n    12. Self-harm or harm to others, including suicide, cutting,
+      and eating disorders\\n    13. Any content intended to incite or promote violence,
+      abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
+      deceive or mislead others, including use of Llama 3.2 related to the following:\\n
+      \   14. Generating, promoting, or furthering fraud or the creation or promotion
+      of disinformation\\n    15. Generating, promoting, or furthering defamatory
+      content, including the creation of defamatory statements, images, or other content\\n
+      \   16. Generating, promoting, or further distributing spam\\n    17. Impersonating
+      another individual without consent, authorization, or legal right\\n    18.
+      Representing that the use of Llama 3.2 or outputs are human-generated\\n    19.
+      Generating or facilitating false online engagement, including fake reviews and
+      other means of fake online engagement\\n4. Fail to appropriately disclose to
+      end users any known dangers of your AI system\\n5. Interact with third party
+      tools, models, or software designed to generate unlawful content or engage in
+      unlawful or harmful conduct and/or represent that the outputs of such tools,
+      models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
+      to any multimodal models included in Llama 3.2, the rights granted under Section
+      1(a) of the Llama 3.2 Community License Agreement are not being granted to you
+      if you are an individual domiciled in, or a company with a principal place of
+      business in, the European Union. This restriction does not apply to end users
+      of a product or service that incorporates any such multimodal models.\\n\\nPlease
+      report any violation of this Policy, software \u201Cbug,\u201D or other problems
+      that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
+      Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
+      Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
+      Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
+      Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
+      3.2: LlamaUseReport@meta.com\\\"\\n\",\"parameters\":\"stop                           \\\"\\u003c|start_header_id|\\u003e\\\"\\nstop
+      \                          \\\"\\u003c|end_header_id|\\u003e\\\"\\nstop                           \\\"\\u003c|eot_id|\\u003e\\\"\",\"template\":\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
+      Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
+      if .Tools }}When you receive a tool call response, use the output to format
+      an answer to the orginal user question.\\n\\nYou are a helpful assistant with
+      tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
+      $_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
+      if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
+      if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
+      a JSON for a function call with its proper arguments that best answers the given
+      prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
+      dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
+      $.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
+      else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
+      end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
+      if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
+      }}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
+      .Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
+      else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
+      .Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
+      end }}\\n{{- end }}\\n{{- end }}\",\"details\":{\"parent_model\":\"\",\"format\":\"gguf\",\"family\":\"llama\",\"families\":[\"llama\"],\"parameter_size\":\"3.2B\",\"quantization_level\":\"Q4_K_M\"},\"model_info\":{\"general.architecture\":\"llama\",\"general.basename\":\"Llama-3.2\",\"general.file_type\":15,\"general.finetune\":\"Instruct\",\"general.languages\":[\"en\",\"de\",\"fr\",\"it\",\"pt\",\"hi\",\"es\",\"th\"],\"general.parameter_count\":3212749888,\"general.quantization_version\":2,\"general.size_label\":\"3B\",\"general.tags\":[\"facebook\",\"meta\",\"pytorch\",\"llama\",\"llama-3\",\"text-generation\"],\"general.type\":\"model\",\"llama.attention.head_count\":24,\"llama.attention.head_count_kv\":8,\"llama.attention.key_length\":128,\"llama.attention.layer_norm_rms_epsilon\":0.00001,\"llama.attention.value_length\":128,\"llama.block_count\":28,\"llama.context_length\":131072,\"llama.embedding_length\":3072,\"llama.feed_forward_length\":8192,\"llama.rope.dimension_count\":128,\"llama.rope.freq_base\":500000,\"llama.vocab_size\":128256,\"tokenizer.ggml.bos_token_id\":128000,\"tokenizer.ggml.eos_token_id\":128009,\"tokenizer.ggml.merges\":null,\"tokenizer.ggml.model\":\"gpt2\",\"tokenizer.ggml.pre\":\"llama-bpe\",\"tokenizer.ggml.token_type\":null,\"tokenizer.ggml.tokens\":null},\"modified_at\":\"2024-12-31T11:53:14.529771974-05:00\"}"
+    headers:
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Tue, 31 Dec 2024 16:56:15 GMT
+      Transfer-Encoding:
+      - chunked
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"name": "llama3.2:3b"}'
+    headers:
+      accept:
+      - '*/*'
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '23'
+      content-type:
+      - application/json
+      host:
+      - localhost:11434
+      user-agent:
+      - litellm/1.56.4
+    method: POST
+    uri: http://localhost:11434/api/show
+  response:
+    content: "{\"license\":\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version
+      Release Date: September 25, 2024\\n\\n\u201CAgreement\u201D means the terms
+      and conditions for use, reproduction, distribution \\nand modification of the
+      Llama Materials set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications,
+      manuals and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
+      or \u201Cyou\u201D means you, or your employer or any other person or entity
+      (if you are \\nentering into this Agreement on such person or entity\u2019s
+      behalf), of the age required under\\napplicable laws, rules or regulations to
+      provide legal consent and that has legal authority\\nto bind your employer or
+      such other person or entity if you are entering in this Agreement\\non their
+      behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
+      and software and algorithms, including\\nmachine-learning model code, trained
+      model weights, inference-enabling code, training-enabling code,\\nfine-tuning
+      enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
+      Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
+      (and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
+      or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
+      or, \\nif you are an entity, your principal place of business is in the EEA
+      or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
+      EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
+      or distributing any portion or element of the Llama Materials,\\nyou agree to
+      be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
+      \   a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
+      and royalty-free limited license under Meta\u2019s intellectual property or
+      other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
+      distribute, copy, create derivative works \\nof, and make modifications to the
+      Llama Materials.  \\n\\n    b. Redistribution and Use.  \\n\\n        i. If
+      you distribute or make available the Llama Materials (or any derivative works
+      thereof), \\nor a product or service (including another AI model) that contains
+      any of them, you shall (A) provide\\na copy of this Agreement with any such
+      Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
+      a related website, user interface, blogpost, about page, or product documentation.
+      If you use the\\nLlama Materials or any outputs or results of the Llama Materials
+      to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
+      or made available, you shall also include \u201CLlama\u201D\\nat the beginning
+      of any such AI model name.\\n\\n        ii. If you receive Llama Materials,
+      or any derivative works thereof, from a Licensee as part\\nof an integrated
+      end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
+      \       iii. You must retain in all copies of the Llama Materials that you distribute
+      the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
+      as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
+      Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
+      \       iv. Your use of the Llama Materials must comply with applicable laws
+      and regulations\\n(including trade compliance laws and regulations) and adhere
+      to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
+      which is hereby \\nincorporated by reference into this Agreement.\\n  \\n2.
+      Additional Commercial Terms. If, on the Llama 3.2 version release date, the
+      monthly active users\\nof the products or services made available by or for
+      Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
+      active users in the preceding calendar month, you must request \\na license
+      from Meta, which Meta may grant to you in its sole discretion, and you are not
+      authorized to\\nexercise any of the rights under this Agreement unless or until
+      Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
+      UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
+      THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
+      ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
+      IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
+      MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
+      DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
+      AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
+      OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
+      ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
+      TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
+      \\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
+      EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
+      OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
+      \   a. No trademark licenses are granted under this Agreement, and in connection
+      with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
+      owned by or associated with the other or any of its affiliates, \\nexcept as
+      required for reasonable and customary use in describing and redistributing the
+      Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
+      you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
+      \\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
+      brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
+      All goodwill arising out of your use of the Mark \\nwill inure to the benefit
+      of Meta.\\n\\n    b. Subject to Meta\u2019s ownership of Llama Materials and
+      derivatives made by or for Meta, with respect to any\\n    derivative works
+      and modifications of the Llama Materials that are made by you, as between you
+      and Meta,\\n    you are and will be the owner of such derivative works and modifications.\\n\\n
+      \   c. If you institute litigation or other proceedings against Meta or any
+      entity (including a cross-claim or\\n    counterclaim in a lawsuit) alleging
+      that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
+      \   of any of the foregoing, constitutes infringement of intellectual property
+      or other rights owned or licensable\\n    by you, then any licenses granted
+      to you under this Agreement shall terminate as of the date such litigation or\\n
+      \   claim is filed or instituted. You will indemnify and hold harmless Meta
+      from and against any claim by any third\\n    party arising out of or related
+      to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
+      The term of this Agreement will commence upon your acceptance of this Agreement
+      or access\\nto the Llama Materials and will continue in full force and effect
+      until terminated in accordance with the terms\\nand conditions herein. Meta
+      may terminate this Agreement if you are in breach of any term or condition of
+      this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
+      use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
+      of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
+      be governed and construed under the laws of the State of \\nCalifornia without
+      regard to choice of law principles, and the UN Convention on Contracts for the
+      International\\nSale of Goods does not apply to this Agreement. The courts of
+      California shall have exclusive jurisdiction of\\nany dispute arising out of
+      this Agreement.\\n**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta is committed
+      to promoting safe and fair use of its tools and features, including Llama 3.2.
+      If you access or use Llama 3.2, you agree to this Acceptable Use Policy (\u201C**Policy**\u201D).
+      The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
+      Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
+      you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
+      the law or others\u2019 rights, including to:\\n    1. Engage in, promote, generate,
+      contribute to, encourage, plan, incite, or further illegal or unlawful activity
+      or content, such as:\\n        1. Violence or terrorism\\n        2. Exploitation
+      or harm to children, including the solicitation, creation, acquisition, or dissemination
+      of child exploitative content or failure to report Child Sexual Abuse Material\\n
+      \       3. Human trafficking, exploitation, and sexual violence\\n        4.
+      The illegal distribution of information or materials to minors, including obscene
+      materials, or failure to employ legally required age-gating in connection with
+      such information or materials.\\n        5. Sexual solicitation\\n        6.
+      Any other criminal activity\\n    1. Engage in, promote, incite, or facilitate
+      the harassment, abuse, threatening, or bullying of individuals or groups of
+      individuals\\n    2. Engage in, promote, incite, or facilitate discrimination
+      or other unlawful or harmful conduct in the provision of employment, employment
+      benefits, credit, housing, other economic benefits, or other essential goods
+      and services\\n    3. Engage in the unauthorized or unlicensed practice of any
+      profession including, but not limited to, financial, legal, medical/health,
+      or related professional practices\\n    4. Collect, process, disclose, generate,
+      or infer private or sensitive information about individuals, including information
+      about individuals\u2019 identity, health, or demographic information, unless
+      you have obtained the right to do so in accordance with applicable law\\n    5.
+      Engage in or facilitate any action or generate any content that infringes, misappropriates,
+      or otherwise violates any third-party rights, including the outputs or results
+      of any products or services using the Llama Materials\\n    6. Create, generate,
+      or facilitate the creation of malicious code, malware, computer viruses or do
+      anything else that could disable, overburden, interfere with or impair the proper
+      working, integrity, operation or appearance of a website or computer system\\n
+      \   7. Engage in any action, or facilitate any action, to intentionally circumvent
+      or remove usage restrictions or other safety measures, or to enable functionality
+      disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
+      planning or development of activities that present a risk of death or bodily
+      harm to individuals, including use of Llama 3.2 related to the following:\\n
+      \   8. Military, warfare, nuclear industries or applications, espionage, use
+      for materials or activities that are subject to the International Traffic Arms
+      Regulations (ITAR) maintained by the United States Department of State or to
+      the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
+      Convention Implementation Act of 1997\\n    9. Guns and illegal weapons (including
+      weapon development)\\n    10. Illegal drugs and regulated/controlled substances\\n
+      \   11. Operation of critical infrastructure, transportation technologies, or
+      heavy machinery\\n    12. Self-harm or harm to others, including suicide, cutting,
+      and eating disorders\\n    13. Any content intended to incite or promote violence,
+      abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
+      deceive or mislead others, including use of Llama 3.2 related to the following:\\n
+      \   14. Generating, promoting, or furthering fraud or the creation or promotion
+      of disinformation\\n    15. Generating, promoting, or furthering defamatory
+      content, including the creation of defamatory statements, images, or other content\\n
+      \   16. Generating, promoting, or further distributing spam\\n    17. Impersonating
+      another individual without consent, authorization, or legal right\\n    18.
+      Representing that the use of Llama 3.2 or outputs are human-generated\\n    19.
+      Generating or facilitating false online engagement, including fake reviews and
+      other means of fake online engagement\\n4. Fail to appropriately disclose to
+      end users any known dangers of your AI system\\n5. Interact with third party
+      tools, models, or software designed to generate unlawful content or engage in
+      unlawful or harmful conduct and/or represent that the outputs of such tools,
+      models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
+      to any multimodal models included in Llama 3.2, the rights granted under Section
+      1(a) of the Llama 3.2 Community License Agreement are not being granted to you
+      if you are an individual domiciled in, or a company with a principal place of
+      business in, the European Union. This restriction does not apply to end users
+      of a product or service that incorporates any such multimodal models.\\n\\nPlease
+      report any violation of this Policy, software \u201Cbug,\u201D or other problems
+      that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
+      Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
+      Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
+      Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
+      Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
+      3.2: LlamaUseReport@meta.com\",\"modelfile\":\"# Modelfile generated by \\\"ollama
+      show\\\"\\n# To build a new Modelfile based on this, replace FROM with:\\n#
+      FROM llama3.2:3b\\n\\nFROM /Users/brandonhancock/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff\\nTEMPLATE
+      \\\"\\\"\\\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
+      Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
+      if .Tools }}When you receive a tool call response, use the output to format
+      an answer to the orginal user question.\\n\\nYou are a helpful assistant with
+      tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
+      $_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
+      if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
+      if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
+      a JSON for a function call with its proper arguments that best answers the given
+      prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
+      dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
+      $.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
+      else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
+      end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
+      if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
+      }}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
+      .Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
+      else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
+      .Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
+      end }}\\n{{- end }}\\n{{- end }}\\\"\\\"\\\"\\nPARAMETER stop \\u003c|start_header_id|\\u003e\\nPARAMETER
+      stop \\u003c|end_header_id|\\u003e\\nPARAMETER stop \\u003c|eot_id|\\u003e\\nLICENSE
+      \\\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version Release Date:
+      September 25, 2024\\n\\n\u201CAgreement\u201D means the terms and conditions
+      for use, reproduction, distribution \\nand modification of the Llama Materials
+      set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications, manuals
+      and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
+      or \u201Cyou\u201D means you, or your employer or any other person or entity
+      (if you are \\nentering into this Agreement on such person or entity\u2019s
+      behalf), of the age required under\\napplicable laws, rules or regulations to
+      provide legal consent and that has legal authority\\nto bind your employer or
+      such other person or entity if you are entering in this Agreement\\non their
+      behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
+      and software and algorithms, including\\nmachine-learning model code, trained
+      model weights, inference-enabling code, training-enabling code,\\nfine-tuning
+      enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
+      Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
+      (and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
+      or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
+      or, \\nif you are an entity, your principal place of business is in the EEA
+      or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
+      EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
+      or distributing any portion or element of the Llama Materials,\\nyou agree to
+      be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
+      \   a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
+      and royalty-free limited license under Meta\u2019s intellectual property or
+      other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
+      distribute, copy, create derivative works \\nof, and make modifications to the
+      Llama Materials.  \\n\\n    b. Redistribution and Use.  \\n\\n        i. If
+      you distribute or make available the Llama Materials (or any derivative works
+      thereof), \\nor a product or service (including another AI model) that contains
+      any of them, you shall (A) provide\\na copy of this Agreement with any such
+      Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
+      a related website, user interface, blogpost, about page, or product documentation.
+      If you use the\\nLlama Materials or any outputs or results of the Llama Materials
+      to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
+      or made available, you shall also include \u201CLlama\u201D\\nat the beginning
+      of any such AI model name.\\n\\n        ii. If you receive Llama Materials,
+      or any derivative works thereof, from a Licensee as part\\nof an integrated
+      end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
+      \       iii. You must retain in all copies of the Llama Materials that you distribute
+      the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
+      as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
+      Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
+      \       iv. Your use of the Llama Materials must comply with applicable laws
+      and regulations\\n(including trade compliance laws and regulations) and adhere
+      to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
+      which is hereby \\nincorporated by reference into this Agreement.\\n  \\n2.
+      Additional Commercial Terms. If, on the Llama 3.2 version release date, the
+      monthly active users\\nof the products or services made available by or for
+      Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
+      active users in the preceding calendar month, you must request \\na license
+      from Meta, which Meta may grant to you in its sole discretion, and you are not
+      authorized to\\nexercise any of the rights under this Agreement unless or until
+      Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
+      UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
+      THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
+      ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
+      IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
+      MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
+      DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
+      AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
+      OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
+      ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
+      TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
+      \\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
+      EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
+      OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
+      \   a. No trademark licenses are granted under this Agreement, and in connection
+      with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
+      owned by or associated with the other or any of its affiliates, \\nexcept as
+      required for reasonable and customary use in describing and redistributing the
+      Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
+      you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
+      \\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
+      brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
+      All goodwill arising out of your use of the Mark \\nwill inure to the benefit
+      of Meta.\\n\\n    b. Subject to Meta\u2019s ownership of Llama Materials and
+      derivatives made by or for Meta, with respect to any\\n    derivative works
+      and modifications of the Llama Materials that are made by you, as between you
+      and Meta,\\n    you are and will be the owner of such derivative works and modifications.\\n\\n
+      \   c. If you institute litigation or other proceedings against Meta or any
+      entity (including a cross-claim or\\n    counterclaim in a lawsuit) alleging
+      that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
+      \   of any of the foregoing, constitutes infringement of intellectual property
+      or other rights owned or licensable\\n    by you, then any licenses granted
+      to you under this Agreement shall terminate as of the date such litigation or\\n
+      \   claim is filed or instituted. You will indemnify and hold harmless Meta
+      from and against any claim by any third\\n    party arising out of or related
+      to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
+      The term of this Agreement will commence upon your acceptance of this Agreement
+      or access\\nto the Llama Materials and will continue in full force and effect
+      until terminated in accordance with the terms\\nand conditions herein. Meta
+      may terminate this Agreement if you are in breach of any term or condition of
+      this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
+      use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
+      of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
+      be governed and construed under the laws of the State of \\nCalifornia without
+      regard to choice of law principles, and the UN Convention on Contracts for the
+      International\\nSale of Goods does not apply to this Agreement. The courts of
+      California shall have exclusive jurisdiction of\\nany dispute arising out of
+      this Agreement.\\\"\\nLICENSE \\\"**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta
+      is committed to promoting safe and fair use of its tools and features, including
+      Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use
+      Policy (\u201C**Policy**\u201D). The most recent copy of this policy can be
+      found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
+      Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
+      you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
+      the law or others\u2019 rights, including to:\\n    1. Engage in, promote, generate,
+      contribute to, encourage, plan, incite, or further illegal or unlawful activity
+      or content, such as:\\n        1. Violence or terrorism\\n        2. Exploitation
+      or harm to children, including the solicitation, creation, acquisition, or dissemination
+      of child exploitative content or failure to report Child Sexual Abuse Material\\n
+      \       3. Human trafficking, exploitation, and sexual violence\\n        4.
+      The illegal distribution of information or materials to minors, including obscene
+      materials, or failure to employ legally required age-gating in connection with
+      such information or materials.\\n        5. Sexual solicitation\\n        6.
+      Any other criminal activity\\n    1. Engage in, promote, incite, or facilitate
+      the harassment, abuse, threatening, or bullying of individuals or groups of
+      individuals\\n    2. Engage in, promote, incite, or facilitate discrimination
+      or other unlawful or harmful conduct in the provision of employment, employment
+      benefits, credit, housing, other economic benefits, or other essential goods
+      and services\\n    3. Engage in the unauthorized or unlicensed practice of any
+      profession including, but not limited to, financial, legal, medical/health,
+      or related professional practices\\n    4. Collect, process, disclose, generate,
+      or infer private or sensitive information about individuals, including information
+      about individuals\u2019 identity, health, or demographic information, unless
+      you have obtained the right to do so in accordance with applicable law\\n    5.
+      Engage in or facilitate any action or generate any content that infringes, misappropriates,
+      or otherwise violates any third-party rights, including the outputs or results
+      of any products or services using the Llama Materials\\n    6. Create, generate,
+      or facilitate the creation of malicious code, malware, computer viruses or do
+      anything else that could disable, overburden, interfere with or impair the proper
+      working, integrity, operation or appearance of a website or computer system\\n
+      \   7. Engage in any action, or facilitate any action, to intentionally circumvent
+      or remove usage restrictions or other safety measures, or to enable functionality
+      disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
+      planning or development of activities that present a risk of death or bodily
+      harm to individuals, including use of Llama 3.2 related to the following:\\n
+      \   8. Military, warfare, nuclear industries or applications, espionage, use
+      for materials or activities that are subject to the International Traffic Arms
+      Regulations (ITAR) maintained by the United States Department of State or to
+      the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
+      Convention Implementation Act of 1997\\n    9. Guns and illegal weapons (including
+      weapon development)\\n    10. Illegal drugs and regulated/controlled substances\\n
+      \   11. Operation of critical infrastructure, transportation technologies, or
+      heavy machinery\\n    12. Self-harm or harm to others, including suicide, cutting,
+      and eating disorders\\n    13. Any content intended to incite or promote violence,
+      abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
+      deceive or mislead others, including use of Llama 3.2 related to the following:\\n
+      \   14. Generating, promoting, or furthering fraud or the creation or promotion
+      of disinformation\\n    15. Generating, promoting, or furthering defamatory
+      content, including the creation of defamatory statements, images, or other content\\n
+      \   16. Generating, promoting, or further distributing spam\\n    17. Impersonating
+      another individual without consent, authorization, or legal right\\n    18.
+      Representing that the use of Llama 3.2 or outputs are human-generated\\n    19.
+      Generating or facilitating false online engagement, including fake reviews and
+      other means of fake online engagement\\n4. Fail to appropriately disclose to
+      end users any known dangers of your AI system\\n5. Interact with third party
+      tools, models, or software designed to generate unlawful content or engage in
+      unlawful or harmful conduct and/or represent that the outputs of such tools,
+      models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
+      to any multimodal models included in Llama 3.2, the rights granted under Section
+      1(a) of the Llama 3.2 Community License Agreement are not being granted to you
+      if you are an individual domiciled in, or a company with a principal place of
+      business in, the European Union. This restriction does not apply to end users
+      of a product or service that incorporates any such multimodal models.\\n\\nPlease
+      report any violation of this Policy, software \u201Cbug,\u201D or other problems
+      that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
+      Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
+      Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
+      Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
+      Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
+      3.2: LlamaUseReport@meta.com\\\"\\n\",\"parameters\":\"stop                           \\\"\\u003c|start_header_id|\\u003e\\\"\\nstop
+      \                          \\\"\\u003c|end_header_id|\\u003e\\\"\\nstop                           \\\"\\u003c|eot_id|\\u003e\\\"\",\"template\":\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
+      Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
+      if .Tools }}When you receive a tool call response, use the output to format
+      an answer to the orginal user question.\\n\\nYou are a helpful assistant with
+      tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
+      $_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
+      if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
+      if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
+      a JSON for a function call with its proper arguments that best answers the given
+      prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
+      dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
+      $.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
+      else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
+      end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
+      if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
+      }}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
+      .Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
+      else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
+      .Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
+      end }}\\n{{- end }}\\n{{- end }}\",\"details\":{\"parent_model\":\"\",\"format\":\"gguf\",\"family\":\"llama\",\"families\":[\"llama\"],\"parameter_size\":\"3.2B\",\"quantization_level\":\"Q4_K_M\"},\"model_info\":{\"general.architecture\":\"llama\",\"general.basename\":\"Llama-3.2\",\"general.file_type\":15,\"general.finetune\":\"Instruct\",\"general.languages\":[\"en\",\"de\",\"fr\",\"it\",\"pt\",\"hi\",\"es\",\"th\"],\"general.parameter_count\":3212749888,\"general.quantization_version\":2,\"general.size_label\":\"3B\",\"general.tags\":[\"facebook\",\"meta\",\"pytorch\",\"llama\",\"llama-3\",\"text-generation\"],\"general.type\":\"model\",\"llama.attention.head_count\":24,\"llama.attention.head_count_kv\":8,\"llama.attention.key_length\":128,\"llama.attention.layer_norm_rms_epsilon\":0.00001,\"llama.attention.value_length\":128,\"llama.block_count\":28,\"llama.context_length\":131072,\"llama.embedding_length\":3072,\"llama.feed_forward_length\":8192,\"llama.rope.dimension_count\":128,\"llama.rope.freq_base\":500000,\"llama.vocab_size\":128256,\"tokenizer.ggml.bos_token_id\":128000,\"tokenizer.ggml.eos_token_id\":128009,\"tokenizer.ggml.merges\":null,\"tokenizer.ggml.model\":\"gpt2\",\"tokenizer.ggml.pre\":\"llama-bpe\",\"tokenizer.ggml.token_type\":null,\"tokenizer.ggml.tokens\":null},\"modified_at\":\"2024-12-31T11:53:14.529771974-05:00\"}"
+    headers:
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Tue, 31 Dec 2024 16:56:15 GMT
+      Transfer-Encoding:
+      - chunked
+    http_version: HTTP/1.1
+    status_code: 200
 version: 1

tests/cassettes/test_agent_with_ollama_llama3.yaml

@@ -1,36 +1,863 @@
 interactions:
 - request:
     body: '{"model": "llama3.2:3b", "prompt": "### User:\nRespond in 20 words. Who
-      which model are you?\n\n", "options": {"stop": ["\nObservation:"]}, "stream":
+      are you?\n\n", "options": {"stop": ["\nObservation:"]}, "stream": false}'
-      false}'
     headers:
-      Accept:
+      accept:
       - '*/*'
-      Accept-Encoding:
+      accept-encoding:
       - gzip, deflate
-      Connection:
+      connection:
       - keep-alive
-      Content-Length:
+      content-length:
-      - '156'
+      - '144'
-      Content-Type:
+      host:
-      - application/json
+      - localhost:11434
-      User-Agent:
+      user-agent:
-      - python-requests/2.32.3
+      - litellm/1.56.4
     method: POST
     uri: http://localhost:11434/api/generate
   response:
-    body:
+    content: '{"model":"llama3.2:3b","created_at":"2024-12-31T16:57:54.063894Z","response":"I''m
-      string: '{"model":"llama3.2:3b","created_at":"2025-01-02T20:07:07.623404Z","response":"I''m
+      an AI designed to provide information and assist with inquiries, while maintaining
-        an AI designed to assist and communicate with users, utilizing a combination
+      a neutral and respectful tone always.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,2724,512,66454,304,220,508,4339,13,10699,527,499,1980,128009,128006,78191,128007,271,40,2846,459,15592,6319,311,3493,2038,323,7945,449,44983,11,1418,20958,264,21277,323,49150,16630,2744,13],"total_duration":651386042,"load_duration":41061917,"prompt_eval_count":38,"prompt_eval_duration":204000000,"eval_count":23,"eval_duration":405000000}'
-        of natural language processing models.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,2724,512,66454,304,220,508,4339,13,10699,902,1646,527,499,1980,128009,128006,78191,128007,271,40,2846,459,15592,6319,311,7945,323,19570,449,3932,11,35988,264,10824,315,5933,4221,8863,4211,13],"total_duration":1076617833,"load_duration":46505416,"prompt_eval_count":40,"prompt_eval_duration":626000000,"eval_count":22,"eval_duration":399000000}'
     headers:
       Content-Length:
-      - '690'
+      - '692'
       Content-Type:
       - application/json; charset=utf-8
       Date:
-      - Thu, 02 Jan 2025 20:07:07 GMT
+      - Tue, 31 Dec 2024 16:57:54 GMT
-    status:
+    http_version: HTTP/1.1
-      code: 200
+    status_code: 200
-      message: OK
+- request:
+    body: '{"name": "llama3.2:3b"}'
+    headers:
+      accept:
+      - '*/*'
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '23'
+      content-type:
+      - application/json
+      host:
+      - localhost:11434
+      user-agent:
+      - litellm/1.56.4
+    method: POST
+    uri: http://localhost:11434/api/show
+  response:
+    content: "{\"license\":\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version
+      Release Date: September 25, 2024\\n\\n\u201CAgreement\u201D means the terms
+      and conditions for use, reproduction, distribution \\nand modification of the
+      Llama Materials set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications,
+      manuals and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
+      or \u201Cyou\u201D means you, or your employer or any other person or entity
+      (if you are \\nentering into this Agreement on such person or entity\u2019s
+      behalf), of the age required under\\napplicable laws, rules or regulations to
+      provide legal consent and that has legal authority\\nto bind your employer or
+      such other person or entity if you are entering in this Agreement\\non their
+      behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
+      and software and algorithms, including\\nmachine-learning model code, trained
+      model weights, inference-enabling code, training-enabling code,\\nfine-tuning
+      enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
+      Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
+      (and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
+      or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
+      or, \\nif you are an entity, your principal place of business is in the EEA
+      or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
+      EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
+      or distributing any portion or element of the Llama Materials,\\nyou agree to
+      be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
+      \   a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
+      and royalty-free limited license under Meta\u2019s intellectual property or
+      other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
+      distribute, copy, create derivative works \\nof, and make modifications to the
+      Llama Materials.  \\n\\n    b. Redistribution and Use.  \\n\\n        i. If
+      you distribute or make available the Llama Materials (or any derivative works
+      thereof), \\nor a product or service (including another AI model) that contains
+      any of them, you shall (A) provide\\na copy of this Agreement with any such
+      Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
+      a related website, user interface, blogpost, about page, or product documentation.
+      If you use the\\nLlama Materials or any outputs or results of the Llama Materials
+      to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
+      or made available, you shall also include \u201CLlama\u201D\\nat the beginning
+      of any such AI model name.\\n\\n        ii. If you receive Llama Materials,
+      or any derivative works thereof, from a Licensee as part\\nof an integrated
+      end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
+      \       iii. You must retain in all copies of the Llama Materials that you distribute
+      the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
+      as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
+      Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
+      \       iv. Your use of the Llama Materials must comply with applicable laws
+      and regulations\\n(including trade compliance laws and regulations) and adhere
+      to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
+      which is hereby \\nincorporated by reference into this Agreement.\\n  \\n2.
+      Additional Commercial Terms. If, on the Llama 3.2 version release date, the
+      monthly active users\\nof the products or services made available by or for
+      Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
+      active users in the preceding calendar month, you must request \\na license
+      from Meta, which Meta may grant to you in its sole discretion, and you are not
+      authorized to\\nexercise any of the rights under this Agreement unless or until
+      Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
+      UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
+      THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
+      ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
+      IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
+      MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
+      DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
+      AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
+      OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
+      ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
+      TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
+      \\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
+      EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
+      OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
+      \   a. No trademark licenses are granted under this Agreement, and in connection
+      with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
+      owned by or associated with the other or any of its affiliates, \\nexcept as
+      required for reasonable and customary use in describing and redistributing the
+      Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
+      you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
+      \\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
+      brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
+      All goodwill arising out of your use of the Mark \\nwill inure to the benefit
+      of Meta.\\n\\n    b. Subject to Meta\u2019s ownership of Llama Materials and
+      derivatives made by or for Meta, with respect to any\\n    derivative works
+      and modifications of the Llama Materials that are made by you, as between you
+      and Meta,\\n    you are and will be the owner of such derivative works and modifications.\\n\\n
+      \   c. If you institute litigation or other proceedings against Meta or any
+      entity (including a cross-claim or\\n    counterclaim in a lawsuit) alleging
+      that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
+      \   of any of the foregoing, constitutes infringement of intellectual property
+      or other rights owned or licensable\\n    by you, then any licenses granted
+      to you under this Agreement shall terminate as of the date such litigation or\\n
+      \   claim is filed or instituted. You will indemnify and hold harmless Meta
+      from and against any claim by any third\\n    party arising out of or related
+      to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
+      The term of this Agreement will commence upon your acceptance of this Agreement
+      or access\\nto the Llama Materials and will continue in full force and effect
+      until terminated in accordance with the terms\\nand conditions herein. Meta
+      may terminate this Agreement if you are in breach of any term or condition of
+      this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
+      use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
+      of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
+      be governed and construed under the laws of the State of \\nCalifornia without
+      regard to choice of law principles, and the UN Convention on Contracts for the
+      International\\nSale of Goods does not apply to this Agreement. The courts of
+      California shall have exclusive jurisdiction of\\nany dispute arising out of
+      this Agreement.\\n**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta is committed
+      to promoting safe and fair use of its tools and features, including Llama 3.2.
+      If you access or use Llama 3.2, you agree to this Acceptable Use Policy (\u201C**Policy**\u201D).
+      The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
+      Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
+      you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
+      the law or others\u2019 rights, including to:\\n    1. Engage in, promote, generate,
+      contribute to, encourage, plan, incite, or further illegal or unlawful activity
+      or content, such as:\\n        1. Violence or terrorism\\n        2. Exploitation
+      or harm to children, including the solicitation, creation, acquisition, or dissemination
+      of child exploitative content or failure to report Child Sexual Abuse Material\\n
+      \       3. Human trafficking, exploitation, and sexual violence\\n        4.
+      The illegal distribution of information or materials to minors, including obscene
+      materials, or failure to employ legally required age-gating in connection with
+      such information or materials.\\n        5. Sexual solicitation\\n        6.
+      Any other criminal activity\\n    1. Engage in, promote, incite, or facilitate
+      the harassment, abuse, threatening, or bullying of individuals or groups of
+      individuals\\n    2. Engage in, promote, incite, or facilitate discrimination
+      or other unlawful or harmful conduct in the provision of employment, employment
+      benefits, credit, housing, other economic benefits, or other essential goods
+      and services\\n    3. Engage in the unauthorized or unlicensed practice of any
+      profession including, but not limited to, financial, legal, medical/health,
+      or related professional practices\\n    4. Collect, process, disclose, generate,
+      or infer private or sensitive information about individuals, including information
+      about individuals\u2019 identity, health, or demographic information, unless
+      you have obtained the right to do so in accordance with applicable law\\n    5.
+      Engage in or facilitate any action or generate any content that infringes, misappropriates,
+      or otherwise violates any third-party rights, including the outputs or results
+      of any products or services using the Llama Materials\\n    6. Create, generate,
+      or facilitate the creation of malicious code, malware, computer viruses or do
+      anything else that could disable, overburden, interfere with or impair the proper
+      working, integrity, operation or appearance of a website or computer system\\n
+      \   7. Engage in any action, or facilitate any action, to intentionally circumvent
+      or remove usage restrictions or other safety measures, or to enable functionality
+      disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
+      planning or development of activities that present a risk of death or bodily
+      harm to individuals, including use of Llama 3.2 related to the following:\\n
+      \   8. Military, warfare, nuclear industries or applications, espionage, use
+      for materials or activities that are subject to the International Traffic Arms
+      Regulations (ITAR) maintained by the United States Department of State or to
+      the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
+      Convention Implementation Act of 1997\\n    9. Guns and illegal weapons (including
+      weapon development)\\n    10. Illegal drugs and regulated/controlled substances\\n
+      \   11. Operation of critical infrastructure, transportation technologies, or
+      heavy machinery\\n    12. Self-harm or harm to others, including suicide, cutting,
+      and eating disorders\\n    13. Any content intended to incite or promote violence,
+      abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
+      deceive or mislead others, including use of Llama 3.2 related to the following:\\n
+      \   14. Generating, promoting, or furthering fraud or the creation or promotion
+      of disinformation\\n    15. Generating, promoting, or furthering defamatory
+      content, including the creation of defamatory statements, images, or other content\\n
+      \   16. Generating, promoting, or further distributing spam\\n    17. Impersonating
+      another individual without consent, authorization, or legal right\\n    18.
+      Representing that the use of Llama 3.2 or outputs are human-generated\\n    19.
+      Generating or facilitating false online engagement, including fake reviews and
+      other means of fake online engagement\\n4. Fail to appropriately disclose to
+      end users any known dangers of your AI system\\n5. Interact with third party
+      tools, models, or software designed to generate unlawful content or engage in
+      unlawful or harmful conduct and/or represent that the outputs of such tools,
+      models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
+      to any multimodal models included in Llama 3.2, the rights granted under Section
+      1(a) of the Llama 3.2 Community License Agreement are not being granted to you
+      if you are an individual domiciled in, or a company with a principal place of
+      business in, the European Union. This restriction does not apply to end users
+      of a product or service that incorporates any such multimodal models.\\n\\nPlease
+      report any violation of this Policy, software \u201Cbug,\u201D or other problems
+      that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
+      Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
+      Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
+      Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
+      Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
+      3.2: LlamaUseReport@meta.com\",\"modelfile\":\"# Modelfile generated by \\\"ollama
+      show\\\"\\n# To build a new Modelfile based on this, replace FROM with:\\n#
+      FROM llama3.2:3b\\n\\nFROM /Users/brandonhancock/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff\\nTEMPLATE
+      \\\"\\\"\\\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
+      Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
+      if .Tools }}When you receive a tool call response, use the output to format
+      an answer to the orginal user question.\\n\\nYou are a helpful assistant with
+      tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
+      $_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
+      if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
+      if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
+      a JSON for a function call with its proper arguments that best answers the given
+      prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
+      dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
+      $.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
+      else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
+      end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
+      if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
+      }}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
+      .Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
+      else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
+      .Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
+      end }}\\n{{- end }}\\n{{- end }}\\\"\\\"\\\"\\nPARAMETER stop \\u003c|start_header_id|\\u003e\\nPARAMETER
+      stop \\u003c|end_header_id|\\u003e\\nPARAMETER stop \\u003c|eot_id|\\u003e\\nLICENSE
+      \\\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version Release Date:
+      September 25, 2024\\n\\n\u201CAgreement\u201D means the terms and conditions
+      for use, reproduction, distribution \\nand modification of the Llama Materials
+      set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications, manuals
+      and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
+      or \u201Cyou\u201D means you, or your employer or any other person or entity
+      (if you are \\nentering into this Agreement on such person or entity\u2019s
+      behalf), of the age required under\\napplicable laws, rules or regulations to
+      provide legal consent and that has legal authority\\nto bind your employer or
+      such other person or entity if you are entering in this Agreement\\non their
+      behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
+      and software and algorithms, including\\nmachine-learning model code, trained
+      model weights, inference-enabling code, training-enabling code,\\nfine-tuning
+      enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
+      Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
+      (and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
+      or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
+      or, \\nif you are an entity, your principal place of business is in the EEA
+      or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
+      EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
+      or distributing any portion or element of the Llama Materials,\\nyou agree to
+      be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
+      \   a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
+      and royalty-free limited license under Meta\u2019s intellectual property or
+      other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
+      distribute, copy, create derivative works \\nof, and make modifications to the
+      Llama Materials.  \\n\\n    b. Redistribution and Use.  \\n\\n        i. If
+      you distribute or make available the Llama Materials (or any derivative works
+      thereof), \\nor a product or service (including another AI model) that contains
+      any of them, you shall (A) provide\\na copy of this Agreement with any such
+      Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
+      a related website, user interface, blogpost, about page, or product documentation.
+      If you use the\\nLlama Materials or any outputs or results of the Llama Materials
+      to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
+      or made available, you shall also include \u201CLlama\u201D\\nat the beginning
+      of any such AI model name.\\n\\n        ii. If you receive Llama Materials,
+      or any derivative works thereof, from a Licensee as part\\nof an integrated
+      end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
+      \       iii. You must retain in all copies of the Llama Materials that you distribute
+      the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
+      as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
+      Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
+      \       iv. Your use of the Llama Materials must comply with applicable laws
+      and regulations\\n(including trade compliance laws and regulations) and adhere
+      to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
+      which is hereby \\nincorporated by reference into this Agreement.\\n  \\n2.
+      Additional Commercial Terms. If, on the Llama 3.2 version release date, the
+      monthly active users\\nof the products or services made available by or for
+      Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
+      active users in the preceding calendar month, you must request \\na license
+      from Meta, which Meta may grant to you in its sole discretion, and you are not
+      authorized to\\nexercise any of the rights under this Agreement unless or until
+      Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
+      UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
+      THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
+      ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
+      IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
+      MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
+      DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
+      AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
+      OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
+      ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
+      TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
+      \\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
+      EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
+      OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
+      \   a. No trademark licenses are granted under this Agreement, and in connection
+      with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
+      owned by or associated with the other or any of its affiliates, \\nexcept as
+      required for reasonable and customary use in describing and redistributing the
+      Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
+      you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
+      \\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
+      brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
+      All goodwill arising out of your use of the Mark \\nwill inure to the benefit
+      of Meta.\\n\\n    b. Subject to Meta\u2019s ownership of Llama Materials and
+      derivatives made by or for Meta, with respect to any\\n    derivative works
+      and modifications of the Llama Materials that are made by you, as between you
+      and Meta,\\n    you are and will be the owner of such derivative works and modifications.\\n\\n
+      \   c. If you institute litigation or other proceedings against Meta or any
+      entity (including a cross-claim or\\n    counterclaim in a lawsuit) alleging
+      that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
+      \   of any of the foregoing, constitutes infringement of intellectual property
+      or other rights owned or licensable\\n    by you, then any licenses granted
+      to you under this Agreement shall terminate as of the date such litigation or\\n
+      \   claim is filed or instituted. You will indemnify and hold harmless Meta
+      from and against any claim by any third\\n    party arising out of or related
+      to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
+      The term of this Agreement will commence upon your acceptance of this Agreement
+      or access\\nto the Llama Materials and will continue in full force and effect
+      until terminated in accordance with the terms\\nand conditions herein. Meta
+      may terminate this Agreement if you are in breach of any term or condition of
+      this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
+      use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
+      of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
+      be governed and construed under the laws of the State of \\nCalifornia without
+      regard to choice of law principles, and the UN Convention on Contracts for the
+      International\\nSale of Goods does not apply to this Agreement. The courts of
+      California shall have exclusive jurisdiction of\\nany dispute arising out of
+      this Agreement.\\\"\\nLICENSE \\\"**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta
+      is committed to promoting safe and fair use of its tools and features, including
+      Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use
+      Policy (\u201C**Policy**\u201D). The most recent copy of this policy can be
+      found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
+      Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
+      you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
+      the law or others\u2019 rights, including to:\\n    1. Engage in, promote, generate,
+      contribute to, encourage, plan, incite, or further illegal or unlawful activity
+      or content, such as:\\n        1. Violence or terrorism\\n        2. Exploitation
+      or harm to children, including the solicitation, creation, acquisition, or dissemination
+      of child exploitative content or failure to report Child Sexual Abuse Material\\n
+      \       3. Human trafficking, exploitation, and sexual violence\\n        4.
+      The illegal distribution of information or materials to minors, including obscene
+      materials, or failure to employ legally required age-gating in connection with
+      such information or materials.\\n        5. Sexual solicitation\\n        6.
+      Any other criminal activity\\n    1. Engage in, promote, incite, or facilitate
+      the harassment, abuse, threatening, or bullying of individuals or groups of
+      individuals\\n    2. Engage in, promote, incite, or facilitate discrimination
+      or other unlawful or harmful conduct in the provision of employment, employment
+      benefits, credit, housing, other economic benefits, or other essential goods
+      and services\\n    3. Engage in the unauthorized or unlicensed practice of any
+      profession including, but not limited to, financial, legal, medical/health,
+      or related professional practices\\n    4. Collect, process, disclose, generate,
+      or infer private or sensitive information about individuals, including information
+      about individuals\u2019 identity, health, or demographic information, unless
+      you have obtained the right to do so in accordance with applicable law\\n    5.
+      Engage in or facilitate any action or generate any content that infringes, misappropriates,
+      or otherwise violates any third-party rights, including the outputs or results
+      of any products or services using the Llama Materials\\n    6. Create, generate,
+      or facilitate the creation of malicious code, malware, computer viruses or do
+      anything else that could disable, overburden, interfere with or impair the proper
+      working, integrity, operation or appearance of a website or computer system\\n
+      \   7. Engage in any action, or facilitate any action, to intentionally circumvent
+      or remove usage restrictions or other safety measures, or to enable functionality
+      disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
+      planning or development of activities that present a risk of death or bodily
+      harm to individuals, including use of Llama 3.2 related to the following:\\n
+      \   8. Military, warfare, nuclear industries or applications, espionage, use
+      for materials or activities that are subject to the International Traffic Arms
+      Regulations (ITAR) maintained by the United States Department of State or to
+      the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
+      Convention Implementation Act of 1997\\n    9. Guns and illegal weapons (including
+      weapon development)\\n    10. Illegal drugs and regulated/controlled substances\\n
+      \   11. Operation of critical infrastructure, transportation technologies, or
+      heavy machinery\\n    12. Self-harm or harm to others, including suicide, cutting,
+      and eating disorders\\n    13. Any content intended to incite or promote violence,
+      abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
+      deceive or mislead others, including use of Llama 3.2 related to the following:\\n
+      \   14. Generating, promoting, or furthering fraud or the creation or promotion
+      of disinformation\\n    15. Generating, promoting, or furthering defamatory
+      content, including the creation of defamatory statements, images, or other content\\n
+      \   16. Generating, promoting, or further distributing spam\\n    17. Impersonating
+      another individual without consent, authorization, or legal right\\n    18.
+      Representing that the use of Llama 3.2 or outputs are human-generated\\n    19.
+      Generating or facilitating false online engagement, including fake reviews and
+      other means of fake online engagement\\n4. Fail to appropriately disclose to
+      end users any known dangers of your AI system\\n5. Interact with third party
+      tools, models, or software designed to generate unlawful content or engage in
+      unlawful or harmful conduct and/or represent that the outputs of such tools,
+      models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
+      to any multimodal models included in Llama 3.2, the rights granted under Section
+      1(a) of the Llama 3.2 Community License Agreement are not being granted to you
+      if you are an individual domiciled in, or a company with a principal place of
+      business in, the European Union. This restriction does not apply to end users
+      of a product or service that incorporates any such multimodal models.\\n\\nPlease
+      report any violation of this Policy, software \u201Cbug,\u201D or other problems
+      that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
+      Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
+      Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
+      Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
+      Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
+      3.2: LlamaUseReport@meta.com\\\"\\n\",\"parameters\":\"stop                           \\\"\\u003c|start_header_id|\\u003e\\\"\\nstop
+      \                          \\\"\\u003c|end_header_id|\\u003e\\\"\\nstop                           \\\"\\u003c|eot_id|\\u003e\\\"\",\"template\":\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
+      Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
+      if .Tools }}When you receive a tool call response, use the output to format
+      an answer to the orginal user question.\\n\\nYou are a helpful assistant with
+      tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
+      $_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
+      if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
+      if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
+      a JSON for a function call with its proper arguments that best answers the given
+      prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
+      dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
+      $.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
+      else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
+      end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
+      if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
+      }}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
+      .Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
+      else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
+      .Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
+      end }}\\n{{- end }}\\n{{- end }}\",\"details\":{\"parent_model\":\"\",\"format\":\"gguf\",\"family\":\"llama\",\"families\":[\"llama\"],\"parameter_size\":\"3.2B\",\"quantization_level\":\"Q4_K_M\"},\"model_info\":{\"general.architecture\":\"llama\",\"general.basename\":\"Llama-3.2\",\"general.file_type\":15,\"general.finetune\":\"Instruct\",\"general.languages\":[\"en\",\"de\",\"fr\",\"it\",\"pt\",\"hi\",\"es\",\"th\"],\"general.parameter_count\":3212749888,\"general.quantization_version\":2,\"general.size_label\":\"3B\",\"general.tags\":[\"facebook\",\"meta\",\"pytorch\",\"llama\",\"llama-3\",\"text-generation\"],\"general.type\":\"model\",\"llama.attention.head_count\":24,\"llama.attention.head_count_kv\":8,\"llama.attention.key_length\":128,\"llama.attention.layer_norm_rms_epsilon\":0.00001,\"llama.attention.value_length\":128,\"llama.block_count\":28,\"llama.context_length\":131072,\"llama.embedding_length\":3072,\"llama.feed_forward_length\":8192,\"llama.rope.dimension_count\":128,\"llama.rope.freq_base\":500000,\"llama.vocab_size\":128256,\"tokenizer.ggml.bos_token_id\":128000,\"tokenizer.ggml.eos_token_id\":128009,\"tokenizer.ggml.merges\":null,\"tokenizer.ggml.model\":\"gpt2\",\"tokenizer.ggml.pre\":\"llama-bpe\",\"tokenizer.ggml.token_type\":null,\"tokenizer.ggml.tokens\":null},\"modified_at\":\"2024-12-31T11:53:14.529771974-05:00\"}"
+    headers:
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Tue, 31 Dec 2024 16:57:54 GMT
+      Transfer-Encoding:
+      - chunked
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"name": "llama3.2:3b"}'
+    headers:
+      accept:
+      - '*/*'
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '23'
+      content-type:
+      - application/json
+      host:
+      - localhost:11434
+      user-agent:
+      - litellm/1.56.4
+    method: POST
+    uri: http://localhost:11434/api/show
+  response:
+    content: "{\"license\":\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version
+      Release Date: September 25, 2024\\n\\n\u201CAgreement\u201D means the terms
+      and conditions for use, reproduction, distribution \\nand modification of the
+      Llama Materials set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications,
+      manuals and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
+      or \u201Cyou\u201D means you, or your employer or any other person or entity
+      (if you are \\nentering into this Agreement on such person or entity\u2019s
+      behalf), of the age required under\\napplicable laws, rules or regulations to
+      provide legal consent and that has legal authority\\nto bind your employer or
+      such other person or entity if you are entering in this Agreement\\non their
+      behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
+      and software and algorithms, including\\nmachine-learning model code, trained
+      model weights, inference-enabling code, training-enabling code,\\nfine-tuning
+      enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
+      Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
+      (and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
+      or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
+      or, \\nif you are an entity, your principal place of business is in the EEA
+      or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
+      EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
+      or distributing any portion or element of the Llama Materials,\\nyou agree to
+      be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
+      \   a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
+      and royalty-free limited license under Meta\u2019s intellectual property or
+      other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
+      distribute, copy, create derivative works \\nof, and make modifications to the
+      Llama Materials.  \\n\\n    b. Redistribution and Use.  \\n\\n        i. If
+      you distribute or make available the Llama Materials (or any derivative works
+      thereof), \\nor a product or service (including another AI model) that contains
+      any of them, you shall (A) provide\\na copy of this Agreement with any such
+      Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
+      a related website, user interface, blogpost, about page, or product documentation.
+      If you use the\\nLlama Materials or any outputs or results of the Llama Materials
+      to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
+      or made available, you shall also include \u201CLlama\u201D\\nat the beginning
+      of any such AI model name.\\n\\n        ii. If you receive Llama Materials,
+      or any derivative works thereof, from a Licensee as part\\nof an integrated
+      end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
+      \       iii. You must retain in all copies of the Llama Materials that you distribute
+      the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
+      as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
+      Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
+      \       iv. Your use of the Llama Materials must comply with applicable laws
+      and regulations\\n(including trade compliance laws and regulations) and adhere
+      to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
+      which is hereby \\nincorporated by reference into this Agreement.\\n  \\n2.
+      Additional Commercial Terms. If, on the Llama 3.2 version release date, the
+      monthly active users\\nof the products or services made available by or for
+      Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
+      active users in the preceding calendar month, you must request \\na license
+      from Meta, which Meta may grant to you in its sole discretion, and you are not
+      authorized to\\nexercise any of the rights under this Agreement unless or until
+      Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
+      UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
+      THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
+      ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
+      IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
+      MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
+      DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
+      AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
+      OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
+      ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
+      TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
+      \\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
+      EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
+      OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
+      \   a. No trademark licenses are granted under this Agreement, and in connection
+      with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
+      owned by or associated with the other or any of its affiliates, \\nexcept as
+      required for reasonable and customary use in describing and redistributing the
+      Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
+      you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
+      \\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
+      brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
+      All goodwill arising out of your use of the Mark \\nwill inure to the benefit
+      of Meta.\\n\\n    b. Subject to Meta\u2019s ownership of Llama Materials and
+      derivatives made by or for Meta, with respect to any\\n    derivative works
+      and modifications of the Llama Materials that are made by you, as between you
+      and Meta,\\n    you are and will be the owner of such derivative works and modifications.\\n\\n
+      \   c. If you institute litigation or other proceedings against Meta or any
+      entity (including a cross-claim or\\n    counterclaim in a lawsuit) alleging
+      that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
+      \   of any of the foregoing, constitutes infringement of intellectual property
+      or other rights owned or licensable\\n    by you, then any licenses granted
+      to you under this Agreement shall terminate as of the date such litigation or\\n
+      \   claim is filed or instituted. You will indemnify and hold harmless Meta
+      from and against any claim by any third\\n    party arising out of or related
+      to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
+      The term of this Agreement will commence upon your acceptance of this Agreement
+      or access\\nto the Llama Materials and will continue in full force and effect
+      until terminated in accordance with the terms\\nand conditions herein. Meta
+      may terminate this Agreement if you are in breach of any term or condition of
+      this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
+      use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
+      of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
+      be governed and construed under the laws of the State of \\nCalifornia without
+      regard to choice of law principles, and the UN Convention on Contracts for the
+      International\\nSale of Goods does not apply to this Agreement. The courts of
+      California shall have exclusive jurisdiction of\\nany dispute arising out of
+      this Agreement.\\n**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta is committed
+      to promoting safe and fair use of its tools and features, including Llama 3.2.
+      If you access or use Llama 3.2, you agree to this Acceptable Use Policy (\u201C**Policy**\u201D).
+      The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
+      Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
+      you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
+      the law or others\u2019 rights, including to:\\n    1. Engage in, promote, generate,
+      contribute to, encourage, plan, incite, or further illegal or unlawful activity
+      or content, such as:\\n        1. Violence or terrorism\\n        2. Exploitation
+      or harm to children, including the solicitation, creation, acquisition, or dissemination
+      of child exploitative content or failure to report Child Sexual Abuse Material\\n
+      \       3. Human trafficking, exploitation, and sexual violence\\n        4.
+      The illegal distribution of information or materials to minors, including obscene
+      materials, or failure to employ legally required age-gating in connection with
+      such information or materials.\\n        5. Sexual solicitation\\n        6.
+      Any other criminal activity\\n    1. Engage in, promote, incite, or facilitate
+      the harassment, abuse, threatening, or bullying of individuals or groups of
+      individuals\\n    2. Engage in, promote, incite, or facilitate discrimination
+      or other unlawful or harmful conduct in the provision of employment, employment
+      benefits, credit, housing, other economic benefits, or other essential goods
+      and services\\n    3. Engage in the unauthorized or unlicensed practice of any
+      profession including, but not limited to, financial, legal, medical/health,
+      or related professional practices\\n    4. Collect, process, disclose, generate,
+      or infer private or sensitive information about individuals, including information
+      about individuals\u2019 identity, health, or demographic information, unless
+      you have obtained the right to do so in accordance with applicable law\\n    5.
+      Engage in or facilitate any action or generate any content that infringes, misappropriates,
+      or otherwise violates any third-party rights, including the outputs or results
+      of any products or services using the Llama Materials\\n    6. Create, generate,
+      or facilitate the creation of malicious code, malware, computer viruses or do
+      anything else that could disable, overburden, interfere with or impair the proper
+      working, integrity, operation or appearance of a website or computer system\\n
+      \   7. Engage in any action, or facilitate any action, to intentionally circumvent
+      or remove usage restrictions or other safety measures, or to enable functionality
+      disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
+      planning or development of activities that present a risk of death or bodily
+      harm to individuals, including use of Llama 3.2 related to the following:\\n
+      \   8. Military, warfare, nuclear industries or applications, espionage, use
+      for materials or activities that are subject to the International Traffic Arms
+      Regulations (ITAR) maintained by the United States Department of State or to
+      the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
+      Convention Implementation Act of 1997\\n    9. Guns and illegal weapons (including
+      weapon development)\\n    10. Illegal drugs and regulated/controlled substances\\n
+      \   11. Operation of critical infrastructure, transportation technologies, or
+      heavy machinery\\n    12. Self-harm or harm to others, including suicide, cutting,
+      and eating disorders\\n    13. Any content intended to incite or promote violence,
+      abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
+      deceive or mislead others, including use of Llama 3.2 related to the following:\\n
+      \   14. Generating, promoting, or furthering fraud or the creation or promotion
+      of disinformation\\n    15. Generating, promoting, or furthering defamatory
+      content, including the creation of defamatory statements, images, or other content\\n
+      \   16. Generating, promoting, or further distributing spam\\n    17. Impersonating
+      another individual without consent, authorization, or legal right\\n    18.
+      Representing that the use of Llama 3.2 or outputs are human-generated\\n    19.
+      Generating or facilitating false online engagement, including fake reviews and
+      other means of fake online engagement\\n4. Fail to appropriately disclose to
+      end users any known dangers of your AI system\\n5. Interact with third party
+      tools, models, or software designed to generate unlawful content or engage in
+      unlawful or harmful conduct and/or represent that the outputs of such tools,
+      models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
+      to any multimodal models included in Llama 3.2, the rights granted under Section
+      1(a) of the Llama 3.2 Community License Agreement are not being granted to you
+      if you are an individual domiciled in, or a company with a principal place of
+      business in, the European Union. This restriction does not apply to end users
+      of a product or service that incorporates any such multimodal models.\\n\\nPlease
+      report any violation of this Policy, software \u201Cbug,\u201D or other problems
+      that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
+      Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
+      Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
+      Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
+      Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
+      3.2: LlamaUseReport@meta.com\",\"modelfile\":\"# Modelfile generated by \\\"ollama
+      show\\\"\\n# To build a new Modelfile based on this, replace FROM with:\\n#
+      FROM llama3.2:3b\\n\\nFROM /Users/brandonhancock/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff\\nTEMPLATE
+      \\\"\\\"\\\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
+      Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
+      if .Tools }}When you receive a tool call response, use the output to format
+      an answer to the orginal user question.\\n\\nYou are a helpful assistant with
+      tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
+      $_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
+      if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
+      if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
+      a JSON for a function call with its proper arguments that best answers the given
+      prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
+      dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
+      $.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
+      else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
+      end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
+      if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
+      }}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
+      .Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
+      else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
+      .Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
+      end }}\\n{{- end }}\\n{{- end }}\\\"\\\"\\\"\\nPARAMETER stop \\u003c|start_header_id|\\u003e\\nPARAMETER
+      stop \\u003c|end_header_id|\\u003e\\nPARAMETER stop \\u003c|eot_id|\\u003e\\nLICENSE
+      \\\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version Release Date:
+      September 25, 2024\\n\\n\u201CAgreement\u201D means the terms and conditions
+      for use, reproduction, distribution \\nand modification of the Llama Materials
+      set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications, manuals
+      and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
+      or \u201Cyou\u201D means you, or your employer or any other person or entity
+      (if you are \\nentering into this Agreement on such person or entity\u2019s
+      behalf), of the age required under\\napplicable laws, rules or regulations to
+      provide legal consent and that has legal authority\\nto bind your employer or
+      such other person or entity if you are entering in this Agreement\\non their
+      behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
+      and software and algorithms, including\\nmachine-learning model code, trained
+      model weights, inference-enabling code, training-enabling code,\\nfine-tuning
+      enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
+      Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
+      (and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
+      or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
+      or, \\nif you are an entity, your principal place of business is in the EEA
+      or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
+      EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
+      or distributing any portion or element of the Llama Materials,\\nyou agree to
+      be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
+      \   a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
+      and royalty-free limited license under Meta\u2019s intellectual property or
+      other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
+      distribute, copy, create derivative works \\nof, and make modifications to the
+      Llama Materials.  \\n\\n    b. Redistribution and Use.  \\n\\n        i. If
+      you distribute or make available the Llama Materials (or any derivative works
+      thereof), \\nor a product or service (including another AI model) that contains
+      any of them, you shall (A) provide\\na copy of this Agreement with any such
+      Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
+      a related website, user interface, blogpost, about page, or product documentation.
+      If you use the\\nLlama Materials or any outputs or results of the Llama Materials
+      to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
+      or made available, you shall also include \u201CLlama\u201D\\nat the beginning
+      of any such AI model name.\\n\\n        ii. If you receive Llama Materials,
+      or any derivative works thereof, from a Licensee as part\\nof an integrated
+      end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
+      \       iii. You must retain in all copies of the Llama Materials that you distribute
+      the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
+      as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
+      Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
+      \       iv. Your use of the Llama Materials must comply with applicable laws
+      and regulations\\n(including trade compliance laws and regulations) and adhere
+      to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
+      which is hereby \\nincorporated by reference into this Agreement.\\n  \\n2.
+      Additional Commercial Terms. If, on the Llama 3.2 version release date, the
+      monthly active users\\nof the products or services made available by or for
+      Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
+      active users in the preceding calendar month, you must request \\na license
+      from Meta, which Meta may grant to you in its sole discretion, and you are not
+      authorized to\\nexercise any of the rights under this Agreement unless or until
+      Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
+      UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
+      THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
+      ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
+      IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
+      MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
+      DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
+      AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
+      OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
+      ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
+      TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
+      \\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
+      EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
+      OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
+      \   a. No trademark licenses are granted under this Agreement, and in connection
+      with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
+      owned by or associated with the other or any of its affiliates, \\nexcept as
+      required for reasonable and customary use in describing and redistributing the
+      Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
+      you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
+      \\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
+      brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
+      All goodwill arising out of your use of the Mark \\nwill inure to the benefit
+      of Meta.\\n\\n    b. Subject to Meta\u2019s ownership of Llama Materials and
+      derivatives made by or for Meta, with respect to any\\n    derivative works
+      and modifications of the Llama Materials that are made by you, as between you
+      and Meta,\\n    you are and will be the owner of such derivative works and modifications.\\n\\n
+      \   c. If you institute litigation or other proceedings against Meta or any
+      entity (including a cross-claim or\\n    counterclaim in a lawsuit) alleging
+      that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
+      \   of any of the foregoing, constitutes infringement of intellectual property
+      or other rights owned or licensable\\n    by you, then any licenses granted
+      to you under this Agreement shall terminate as of the date such litigation or\\n
+      \   claim is filed or instituted. You will indemnify and hold harmless Meta
+      from and against any claim by any third\\n    party arising out of or related
+      to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
+      The term of this Agreement will commence upon your acceptance of this Agreement
+      or access\\nto the Llama Materials and will continue in full force and effect
+      until terminated in accordance with the terms\\nand conditions herein. Meta
+      may terminate this Agreement if you are in breach of any term or condition of
+      this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
+      use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
+      of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
+      be governed and construed under the laws of the State of \\nCalifornia without
+      regard to choice of law principles, and the UN Convention on Contracts for the
+      International\\nSale of Goods does not apply to this Agreement. The courts of
+      California shall have exclusive jurisdiction of\\nany dispute arising out of
+      this Agreement.\\\"\\nLICENSE \\\"**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta
+      is committed to promoting safe and fair use of its tools and features, including
+      Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use
+      Policy (\u201C**Policy**\u201D). The most recent copy of this policy can be
+      found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
+      Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
+      you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
+      the law or others\u2019 rights, including to:\\n    1. Engage in, promote, generate,
+      contribute to, encourage, plan, incite, or further illegal or unlawful activity
+      or content, such as:\\n        1. Violence or terrorism\\n        2. Exploitation
+      or harm to children, including the solicitation, creation, acquisition, or dissemination
+      of child exploitative content or failure to report Child Sexual Abuse Material\\n
+      \       3. Human trafficking, exploitation, and sexual violence\\n        4.
+      The illegal distribution of information or materials to minors, including obscene
+      materials, or failure to employ legally required age-gating in connection with
+      such information or materials.\\n        5. Sexual solicitation\\n        6.
+      Any other criminal activity\\n    1. Engage in, promote, incite, or facilitate
+      the harassment, abuse, threatening, or bullying of individuals or groups of
+      individuals\\n    2. Engage in, promote, incite, or facilitate discrimination
+      or other unlawful or harmful conduct in the provision of employment, employment
+      benefits, credit, housing, other economic benefits, or other essential goods
+      and services\\n    3. Engage in the unauthorized or unlicensed practice of any
+      profession including, but not limited to, financial, legal, medical/health,
+      or related professional practices\\n    4. Collect, process, disclose, generate,
+      or infer private or sensitive information about individuals, including information
+      about individuals\u2019 identity, health, or demographic information, unless
+      you have obtained the right to do so in accordance with applicable law\\n    5.
+      Engage in or facilitate any action or generate any content that infringes, misappropriates,
+      or otherwise violates any third-party rights, including the outputs or results
+      of any products or services using the Llama Materials\\n    6. Create, generate,
+      or facilitate the creation of malicious code, malware, computer viruses or do
+      anything else that could disable, overburden, interfere with or impair the proper
+      working, integrity, operation or appearance of a website or computer system\\n
+      \   7. Engage in any action, or facilitate any action, to intentionally circumvent
+      or remove usage restrictions or other safety measures, or to enable functionality
+      disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
+      planning or development of activities that present a risk of death or bodily
+      harm to individuals, including use of Llama 3.2 related to the following:\\n
+      \   8. Military, warfare, nuclear industries or applications, espionage, use
+      for materials or activities that are subject to the International Traffic Arms
+      Regulations (ITAR) maintained by the United States Department of State or to
+      the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
+      Convention Implementation Act of 1997\\n    9. Guns and illegal weapons (including
+      weapon development)\\n    10. Illegal drugs and regulated/controlled substances\\n
+      \   11. Operation of critical infrastructure, transportation technologies, or
+      heavy machinery\\n    12. Self-harm or harm to others, including suicide, cutting,
+      and eating disorders\\n    13. Any content intended to incite or promote violence,
+      abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
+      deceive or mislead others, including use of Llama 3.2 related to the following:\\n
+      \   14. Generating, promoting, or furthering fraud or the creation or promotion
+      of disinformation\\n    15. Generating, promoting, or furthering defamatory
+      content, including the creation of defamatory statements, images, or other content\\n
+      \   16. Generating, promoting, or further distributing spam\\n    17. Impersonating
+      another individual without consent, authorization, or legal right\\n    18.
+      Representing that the use of Llama 3.2 or outputs are human-generated\\n    19.
+      Generating or facilitating false online engagement, including fake reviews and
+      other means of fake online engagement\\n4. Fail to appropriately disclose to
+      end users any known dangers of your AI system\\n5. Interact with third party
+      tools, models, or software designed to generate unlawful content or engage in
+      unlawful or harmful conduct and/or represent that the outputs of such tools,
+      models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
+      to any multimodal models included in Llama 3.2, the rights granted under Section
+      1(a) of the Llama 3.2 Community License Agreement are not being granted to you
+      if you are an individual domiciled in, or a company with a principal place of
+      business in, the European Union. This restriction does not apply to end users
+      of a product or service that incorporates any such multimodal models.\\n\\nPlease
+      report any violation of this Policy, software \u201Cbug,\u201D or other problems
+      that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
+      Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
+      Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
+      Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
+      Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
+      3.2: LlamaUseReport@meta.com\\\"\\n\",\"parameters\":\"stop                           \\\"\\u003c|start_header_id|\\u003e\\\"\\nstop
+      \                          \\\"\\u003c|end_header_id|\\u003e\\\"\\nstop                           \\\"\\u003c|eot_id|\\u003e\\\"\",\"template\":\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
+      Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
+      if .Tools }}When you receive a tool call response, use the output to format
+      an answer to the orginal user question.\\n\\nYou are a helpful assistant with
+      tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
+      $_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
+      if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
+      if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
+      a JSON for a function call with its proper arguments that best answers the given
+      prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
+      dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
+      $.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
+      else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
+      end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
+      if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
+      }}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
+      .Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
+      else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
+      .Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
+      end }}\\n{{- end }}\\n{{- end }}\",\"details\":{\"parent_model\":\"\",\"format\":\"gguf\",\"family\":\"llama\",\"families\":[\"llama\"],\"parameter_size\":\"3.2B\",\"quantization_level\":\"Q4_K_M\"},\"model_info\":{\"general.architecture\":\"llama\",\"general.basename\":\"Llama-3.2\",\"general.file_type\":15,\"general.finetune\":\"Instruct\",\"general.languages\":[\"en\",\"de\",\"fr\",\"it\",\"pt\",\"hi\",\"es\",\"th\"],\"general.parameter_count\":3212749888,\"general.quantization_version\":2,\"general.size_label\":\"3B\",\"general.tags\":[\"facebook\",\"meta\",\"pytorch\",\"llama\",\"llama-3\",\"text-generation\"],\"general.type\":\"model\",\"llama.attention.head_count\":24,\"llama.attention.head_count_kv\":8,\"llama.attention.key_length\":128,\"llama.attention.layer_norm_rms_epsilon\":0.00001,\"llama.attention.value_length\":128,\"llama.block_count\":28,\"llama.context_length\":131072,\"llama.embedding_length\":3072,\"llama.feed_forward_length\":8192,\"llama.rope.dimension_count\":128,\"llama.rope.freq_base\":500000,\"llama.vocab_size\":128256,\"tokenizer.ggml.bos_token_id\":128000,\"tokenizer.ggml.eos_token_id\":128009,\"tokenizer.ggml.merges\":null,\"tokenizer.ggml.model\":\"gpt2\",\"tokenizer.ggml.pre\":\"llama-bpe\",\"tokenizer.ggml.token_type\":null,\"tokenizer.ggml.tokens\":null},\"modified_at\":\"2024-12-31T11:53:14.529771974-05:00\"}"
+    headers:
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Tue, 31 Dec 2024 16:57:54 GMT
+      Transfer-Encoding:
+      - chunked
+    http_version: HTTP/1.1
+    status_code: 200
 version: 1

tests/cassettes/test_llm_call_with_ollama_llama3.yaml

@@ -1,36 +1,449 @@
 interactions:
 - request:
-    body: '{"model": "llama3.2:3b", "prompt": "### User:\nRespond in 20 words. Which
+    body: '{"model": "llama3.2:3b", "prompt": "### User:\nRespond in 20 words. Who
-      model are you??\n\n", "options": {"num_predict": 30, "temperature": 0.7}, "stream":
+      are you?\n\n", "options": {"temperature": 0.7, "num_predict": 30}, "stream":
       false}'
     headers:
-      Accept:
+      accept:
       - '*/*'
-      Accept-Encoding:
+      accept-encoding:
       - gzip, deflate
-      Connection:
+      connection:
       - keep-alive
-      Content-Length:
+      content-length:
-      - '164'
+      - '155'
-      Content-Type:
+      host:
-      - application/json
+      - localhost:11434
-      User-Agent:
+      user-agent:
-      - python-requests/2.32.3
+      - litellm/1.56.4
     method: POST
     uri: http://localhost:11434/api/generate
   response:
-    body:
+    content: '{"model":"llama3.2:3b","created_at":"2024-12-31T17:00:06.295261Z","response":"I''m
-      string: '{"model":"llama3.2:3b","created_at":"2025-01-02T20:24:24.812595Z","response":"I''m
+      an AI assistant, here to provide information and answer questions to the best
-        an AI, specifically a large language model, designed to understand and respond
+      of my abilities and knowledge.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,2724,512,66454,304,220,508,4339,13,10699,527,499,1980,128009,128006,78191,128007,271,40,2846,459,15592,18328,11,1618,311,3493,2038,323,4320,4860,311,279,1888,315,856,18000,323,6677,13],"total_duration":826912750,"load_duration":32648125,"prompt_eval_count":38,"prompt_eval_duration":389000000,"eval_count":23,"eval_duration":404000000}'
-        to user queries with accuracy.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,2724,512,66454,304,220,508,4339,13,16299,1646,527,499,71291,128009,128006,78191,128007,271,40,2846,459,15592,11,11951,264,3544,4221,1646,11,6319,311,3619,323,6013,311,1217,20126,449,13708,13],"total_duration":827817584,"load_duration":41560542,"prompt_eval_count":39,"prompt_eval_duration":384000000,"eval_count":23,"eval_duration":400000000}'
     headers:
       Content-Length:
-      - '683'
+      - '675'
       Content-Type:
       - application/json; charset=utf-8
       Date:
-      - Thu, 02 Jan 2025 20:24:24 GMT
+      - Tue, 31 Dec 2024 17:00:06 GMT
-    status:
+    http_version: HTTP/1.1
-      code: 200
+    status_code: 200
-      message: OK
+- request:
+    body: '{"name": "llama3.2:3b"}'
+    headers:
+      accept:
+      - '*/*'
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '23'
+      content-type:
+      - application/json
+      host:
+      - localhost:11434
+      user-agent:
+      - litellm/1.56.4
+    method: POST
+    uri: http://localhost:11434/api/show
+  response:
+    content: "{\"license\":\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version
+      Release Date: September 25, 2024\\n\\n\u201CAgreement\u201D means the terms
+      and conditions for use, reproduction, distribution \\nand modification of the
+      Llama Materials set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications,
+      manuals and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
+      or \u201Cyou\u201D means you, or your employer or any other person or entity
+      (if you are \\nentering into this Agreement on such person or entity\u2019s
+      behalf), of the age required under\\napplicable laws, rules or regulations to
+      provide legal consent and that has legal authority\\nto bind your employer or
+      such other person or entity if you are entering in this Agreement\\non their
+      behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
+      and software and algorithms, including\\nmachine-learning model code, trained
+      model weights, inference-enabling code, training-enabling code,\\nfine-tuning
+      enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
+      Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
+      (and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
+      or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
+      or, \\nif you are an entity, your principal place of business is in the EEA
+      or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
+      EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
+      or distributing any portion or element of the Llama Materials,\\nyou agree to
+      be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
+      \   a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
+      and royalty-free limited license under Meta\u2019s intellectual property or
+      other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
+      distribute, copy, create derivative works \\nof, and make modifications to the
+      Llama Materials.  \\n\\n    b. Redistribution and Use.  \\n\\n        i. If
+      you distribute or make available the Llama Materials (or any derivative works
+      thereof), \\nor a product or service (including another AI model) that contains
+      any of them, you shall (A) provide\\na copy of this Agreement with any such
+      Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
+      a related website, user interface, blogpost, about page, or product documentation.
+      If you use the\\nLlama Materials or any outputs or results of the Llama Materials
+      to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
+      or made available, you shall also include \u201CLlama\u201D\\nat the beginning
+      of any such AI model name.\\n\\n        ii. If you receive Llama Materials,
+      or any derivative works thereof, from a Licensee as part\\nof an integrated
+      end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
+      \       iii. You must retain in all copies of the Llama Materials that you distribute
+      the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
+      as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
+      Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
+      \       iv. Your use of the Llama Materials must comply with applicable laws
+      and regulations\\n(including trade compliance laws and regulations) and adhere
+      to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
+      which is hereby \\nincorporated by reference into this Agreement.\\n  \\n2.
+      Additional Commercial Terms. If, on the Llama 3.2 version release date, the
+      monthly active users\\nof the products or services made available by or for
+      Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
+      active users in the preceding calendar month, you must request \\na license
+      from Meta, which Meta may grant to you in its sole discretion, and you are not
+      authorized to\\nexercise any of the rights under this Agreement unless or until
+      Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
+      UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
+      THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
+      ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
+      IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
+      MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
+      DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
+      AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
+      OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
+      ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
+      TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
+      \\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
+      EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
+      OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
+      \   a. No trademark licenses are granted under this Agreement, and in connection
+      with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
+      owned by or associated with the other or any of its affiliates, \\nexcept as
+      required for reasonable and customary use in describing and redistributing the
+      Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
+      you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
+      \\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
+      brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
+      All goodwill arising out of your use of the Mark \\nwill inure to the benefit
+      of Meta.\\n\\n    b. Subject to Meta\u2019s ownership of Llama Materials and
+      derivatives made by or for Meta, with respect to any\\n    derivative works
+      and modifications of the Llama Materials that are made by you, as between you
+      and Meta,\\n    you are and will be the owner of such derivative works and modifications.\\n\\n
+      \   c. If you institute litigation or other proceedings against Meta or any
+      entity (including a cross-claim or\\n    counterclaim in a lawsuit) alleging
+      that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
+      \   of any of the foregoing, constitutes infringement of intellectual property
+      or other rights owned or licensable\\n    by you, then any licenses granted
+      to you under this Agreement shall terminate as of the date such litigation or\\n
+      \   claim is filed or instituted. You will indemnify and hold harmless Meta
+      from and against any claim by any third\\n    party arising out of or related
+      to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
+      The term of this Agreement will commence upon your acceptance of this Agreement
+      or access\\nto the Llama Materials and will continue in full force and effect
+      until terminated in accordance with the terms\\nand conditions herein. Meta
+      may terminate this Agreement if you are in breach of any term or condition of
+      this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
+      use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
+      of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
+      be governed and construed under the laws of the State of \\nCalifornia without
+      regard to choice of law principles, and the UN Convention on Contracts for the
+      International\\nSale of Goods does not apply to this Agreement. The courts of
+      California shall have exclusive jurisdiction of\\nany dispute arising out of
+      this Agreement.\\n**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta is committed
+      to promoting safe and fair use of its tools and features, including Llama 3.2.
+      If you access or use Llama 3.2, you agree to this Acceptable Use Policy (\u201C**Policy**\u201D).
+      The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
+      Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
+      you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
+      the law or others\u2019 rights, including to:\\n    1. Engage in, promote, generate,
+      contribute to, encourage, plan, incite, or further illegal or unlawful activity
+      or content, such as:\\n        1. Violence or terrorism\\n        2. Exploitation
+      or harm to children, including the solicitation, creation, acquisition, or dissemination
+      of child exploitative content or failure to report Child Sexual Abuse Material\\n
+      \       3. Human trafficking, exploitation, and sexual violence\\n        4.
+      The illegal distribution of information or materials to minors, including obscene
+      materials, or failure to employ legally required age-gating in connection with
+      such information or materials.\\n        5. Sexual solicitation\\n        6.
+      Any other criminal activity\\n    1. Engage in, promote, incite, or facilitate
+      the harassment, abuse, threatening, or bullying of individuals or groups of
+      individuals\\n    2. Engage in, promote, incite, or facilitate discrimination
+      or other unlawful or harmful conduct in the provision of employment, employment
+      benefits, credit, housing, other economic benefits, or other essential goods
+      and services\\n    3. Engage in the unauthorized or unlicensed practice of any
+      profession including, but not limited to, financial, legal, medical/health,
+      or related professional practices\\n    4. Collect, process, disclose, generate,
+      or infer private or sensitive information about individuals, including information
+      about individuals\u2019 identity, health, or demographic information, unless
+      you have obtained the right to do so in accordance with applicable law\\n    5.
+      Engage in or facilitate any action or generate any content that infringes, misappropriates,
+      or otherwise violates any third-party rights, including the outputs or results
+      of any products or services using the Llama Materials\\n    6. Create, generate,
+      or facilitate the creation of malicious code, malware, computer viruses or do
+      anything else that could disable, overburden, interfere with or impair the proper
+      working, integrity, operation or appearance of a website or computer system\\n
+      \   7. Engage in any action, or facilitate any action, to intentionally circumvent
+      or remove usage restrictions or other safety measures, or to enable functionality
+      disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
+      planning or development of activities that present a risk of death or bodily
+      harm to individuals, including use of Llama 3.2 related to the following:\\n
+      \   8. Military, warfare, nuclear industries or applications, espionage, use
+      for materials or activities that are subject to the International Traffic Arms
+      Regulations (ITAR) maintained by the United States Department of State or to
+      the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
+      Convention Implementation Act of 1997\\n    9. Guns and illegal weapons (including
+      weapon development)\\n    10. Illegal drugs and regulated/controlled substances\\n
+      \   11. Operation of critical infrastructure, transportation technologies, or
+      heavy machinery\\n    12. Self-harm or harm to others, including suicide, cutting,
+      and eating disorders\\n    13. Any content intended to incite or promote violence,
+      abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
+      deceive or mislead others, including use of Llama 3.2 related to the following:\\n
+      \   14. Generating, promoting, or furthering fraud or the creation or promotion
+      of disinformation\\n    15. Generating, promoting, or furthering defamatory
+      content, including the creation of defamatory statements, images, or other content\\n
+      \   16. Generating, promoting, or further distributing spam\\n    17. Impersonating
+      another individual without consent, authorization, or legal right\\n    18.
+      Representing that the use of Llama 3.2 or outputs are human-generated\\n    19.
+      Generating or facilitating false online engagement, including fake reviews and
+      other means of fake online engagement\\n4. Fail to appropriately disclose to
+      end users any known dangers of your AI system\\n5. Interact with third party
+      tools, models, or software designed to generate unlawful content or engage in
+      unlawful or harmful conduct and/or represent that the outputs of such tools,
+      models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
+      to any multimodal models included in Llama 3.2, the rights granted under Section
+      1(a) of the Llama 3.2 Community License Agreement are not being granted to you
+      if you are an individual domiciled in, or a company with a principal place of
+      business in, the European Union. This restriction does not apply to end users
+      of a product or service that incorporates any such multimodal models.\\n\\nPlease
+      report any violation of this Policy, software \u201Cbug,\u201D or other problems
+      that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
+      Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
+      Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
+      Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
+      Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
+      3.2: LlamaUseReport@meta.com\",\"modelfile\":\"# Modelfile generated by \\\"ollama
+      show\\\"\\n# To build a new Modelfile based on this, replace FROM with:\\n#
+      FROM llama3.2:3b\\n\\nFROM /Users/brandonhancock/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff\\nTEMPLATE
+      \\\"\\\"\\\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
+      Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
+      if .Tools }}When you receive a tool call response, use the output to format
+      an answer to the orginal user question.\\n\\nYou are a helpful assistant with
+      tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
+      $_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
+      if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
+      if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
+      a JSON for a function call with its proper arguments that best answers the given
+      prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
+      dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
+      $.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
+      else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
+      end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
+      if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
+      }}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
+      .Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
+      else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
+      .Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
+      end }}\\n{{- end }}\\n{{- end }}\\\"\\\"\\\"\\nPARAMETER stop \\u003c|start_header_id|\\u003e\\nPARAMETER
+      stop \\u003c|end_header_id|\\u003e\\nPARAMETER stop \\u003c|eot_id|\\u003e\\nLICENSE
+      \\\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version Release Date:
+      September 25, 2024\\n\\n\u201CAgreement\u201D means the terms and conditions
+      for use, reproduction, distribution \\nand modification of the Llama Materials
+      set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications, manuals
+      and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
+      or \u201Cyou\u201D means you, or your employer or any other person or entity
+      (if you are \\nentering into this Agreement on such person or entity\u2019s
+      behalf), of the age required under\\napplicable laws, rules or regulations to
+      provide legal consent and that has legal authority\\nto bind your employer or
+      such other person or entity if you are entering in this Agreement\\non their
+      behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
+      and software and algorithms, including\\nmachine-learning model code, trained
+      model weights, inference-enabling code, training-enabling code,\\nfine-tuning
+      enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
+      Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
+      (and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
+      or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
+      or, \\nif you are an entity, your principal place of business is in the EEA
+      or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
+      EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
+      or distributing any portion or element of the Llama Materials,\\nyou agree to
+      be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
+      \   a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
+      and royalty-free limited license under Meta\u2019s intellectual property or
+      other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
+      distribute, copy, create derivative works \\nof, and make modifications to the
+      Llama Materials.  \\n\\n    b. Redistribution and Use.  \\n\\n        i. If
+      you distribute or make available the Llama Materials (or any derivative works
+      thereof), \\nor a product or service (including another AI model) that contains
+      any of them, you shall (A) provide\\na copy of this Agreement with any such
+      Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
+      a related website, user interface, blogpost, about page, or product documentation.
+      If you use the\\nLlama Materials or any outputs or results of the Llama Materials
+      to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
+      or made available, you shall also include \u201CLlama\u201D\\nat the beginning
+      of any such AI model name.\\n\\n        ii. If you receive Llama Materials,
+      or any derivative works thereof, from a Licensee as part\\nof an integrated
+      end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
+      \       iii. You must retain in all copies of the Llama Materials that you distribute
+      the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
+      as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
+      Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
+      \       iv. Your use of the Llama Materials must comply with applicable laws
+      and regulations\\n(including trade compliance laws and regulations) and adhere
+      to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
+      which is hereby \\nincorporated by reference into this Agreement.\\n  \\n2.
+      Additional Commercial Terms. If, on the Llama 3.2 version release date, the
+      monthly active users\\nof the products or services made available by or for
+      Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
+      active users in the preceding calendar month, you must request \\na license
+      from Meta, which Meta may grant to you in its sole discretion, and you are not
+      authorized to\\nexercise any of the rights under this Agreement unless or until
+      Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
+      UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
+      THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
+      ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
+      IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
+      MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
+      DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
+      AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
+      OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
+      ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
+      TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
+      \\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
+      EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
+      OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
+      \   a. No trademark licenses are granted under this Agreement, and in connection
+      with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
+      owned by or associated with the other or any of its affiliates, \\nexcept as
+      required for reasonable and customary use in describing and redistributing the
+      Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
+      you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
+      \\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
+      brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
+      All goodwill arising out of your use of the Mark \\nwill inure to the benefit
+      of Meta.\\n\\n    b. Subject to Meta\u2019s ownership of Llama Materials and
+      derivatives made by or for Meta, with respect to any\\n    derivative works
+      and modifications of the Llama Materials that are made by you, as between you
+      and Meta,\\n    you are and will be the owner of such derivative works and modifications.\\n\\n
+      \   c. If you institute litigation or other proceedings against Meta or any
+      entity (including a cross-claim or\\n    counterclaim in a lawsuit) alleging
+      that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
+      \   of any of the foregoing, constitutes infringement of intellectual property
+      or other rights owned or licensable\\n    by you, then any licenses granted
+      to you under this Agreement shall terminate as of the date such litigation or\\n
+      \   claim is filed or instituted. You will indemnify and hold harmless Meta
+      from and against any claim by any third\\n    party arising out of or related
+      to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
+      The term of this Agreement will commence upon your acceptance of this Agreement
+      or access\\nto the Llama Materials and will continue in full force and effect
+      until terminated in accordance with the terms\\nand conditions herein. Meta
+      may terminate this Agreement if you are in breach of any term or condition of
+      this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
+      use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
+      of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
+      be governed and construed under the laws of the State of \\nCalifornia without
+      regard to choice of law principles, and the UN Convention on Contracts for the
+      International\\nSale of Goods does not apply to this Agreement. The courts of
+      California shall have exclusive jurisdiction of\\nany dispute arising out of
+      this Agreement.\\\"\\nLICENSE \\\"**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta
+      is committed to promoting safe and fair use of its tools and features, including
+      Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use
+      Policy (\u201C**Policy**\u201D). The most recent copy of this policy can be
+      found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
+      Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
+      you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
+      the law or others\u2019 rights, including to:\\n    1. Engage in, promote, generate,
+      contribute to, encourage, plan, incite, or further illegal or unlawful activity
+      or content, such as:\\n        1. Violence or terrorism\\n        2. Exploitation
+      or harm to children, including the solicitation, creation, acquisition, or dissemination
+      of child exploitative content or failure to report Child Sexual Abuse Material\\n
+      \       3. Human trafficking, exploitation, and sexual violence\\n        4.
+      The illegal distribution of information or materials to minors, including obscene
+      materials, or failure to employ legally required age-gating in connection with
+      such information or materials.\\n        5. Sexual solicitation\\n        6.
+      Any other criminal activity\\n    1. Engage in, promote, incite, or facilitate
+      the harassment, abuse, threatening, or bullying of individuals or groups of
+      individuals\\n    2. Engage in, promote, incite, or facilitate discrimination
+      or other unlawful or harmful conduct in the provision of employment, employment
+      benefits, credit, housing, other economic benefits, or other essential goods
+      and services\\n    3. Engage in the unauthorized or unlicensed practice of any
+      profession including, but not limited to, financial, legal, medical/health,
+      or related professional practices\\n    4. Collect, process, disclose, generate,
+      or infer private or sensitive information about individuals, including information
+      about individuals\u2019 identity, health, or demographic information, unless
+      you have obtained the right to do so in accordance with applicable law\\n    5.
+      Engage in or facilitate any action or generate any content that infringes, misappropriates,
+      or otherwise violates any third-party rights, including the outputs or results
+      of any products or services using the Llama Materials\\n    6. Create, generate,
+      or facilitate the creation of malicious code, malware, computer viruses or do
+      anything else that could disable, overburden, interfere with or impair the proper
+      working, integrity, operation or appearance of a website or computer system\\n
+      \   7. Engage in any action, or facilitate any action, to intentionally circumvent
+      or remove usage restrictions or other safety measures, or to enable functionality
+      disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
+      planning or development of activities that present a risk of death or bodily
+      harm to individuals, including use of Llama 3.2 related to the following:\\n
+      \   8. Military, warfare, nuclear industries or applications, espionage, use
+      for materials or activities that are subject to the International Traffic Arms
+      Regulations (ITAR) maintained by the United States Department of State or to
+      the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
+      Convention Implementation Act of 1997\\n    9. Guns and illegal weapons (including
+      weapon development)\\n    10. Illegal drugs and regulated/controlled substances\\n
+      \   11. Operation of critical infrastructure, transportation technologies, or
+      heavy machinery\\n    12. Self-harm or harm to others, including suicide, cutting,
+      and eating disorders\\n    13. Any content intended to incite or promote violence,
+      abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
+      deceive or mislead others, including use of Llama 3.2 related to the following:\\n
+      \   14. Generating, promoting, or furthering fraud or the creation or promotion
+      of disinformation\\n    15. Generating, promoting, or furthering defamatory
+      content, including the creation of defamatory statements, images, or other content\\n
+      \   16. Generating, promoting, or further distributing spam\\n    17. Impersonating
+      another individual without consent, authorization, or legal right\\n    18.
+      Representing that the use of Llama 3.2 or outputs are human-generated\\n    19.
+      Generating or facilitating false online engagement, including fake reviews and
+      other means of fake online engagement\\n4. Fail to appropriately disclose to
+      end users any known dangers of your AI system\\n5. Interact with third party
+      tools, models, or software designed to generate unlawful content or engage in
+      unlawful or harmful conduct and/or represent that the outputs of such tools,
+      models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
+      to any multimodal models included in Llama 3.2, the rights granted under Section
+      1(a) of the Llama 3.2 Community License Agreement are not being granted to you
+      if you are an individual domiciled in, or a company with a principal place of
+      business in, the European Union. This restriction does not apply to end users
+      of a product or service that incorporates any such multimodal models.\\n\\nPlease
+      report any violation of this Policy, software \u201Cbug,\u201D or other problems
+      that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
+      Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
+      Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
+      Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
+      Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
+      3.2: LlamaUseReport@meta.com\\\"\\n\",\"parameters\":\"stop                           \\\"\\u003c|start_header_id|\\u003e\\\"\\nstop
+      \                          \\\"\\u003c|end_header_id|\\u003e\\\"\\nstop                           \\\"\\u003c|eot_id|\\u003e\\\"\",\"template\":\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
+      Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
+      if .Tools }}When you receive a tool call response, use the output to format
+      an answer to the orginal user question.\\n\\nYou are a helpful assistant with
+      tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
+      $_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
+      if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
+      if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
+      a JSON for a function call with its proper arguments that best answers the given
+      prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
+      dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
+      $.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
+      else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
+      end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
+      if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
+      }}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
+      .Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
+      else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
+      .Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
+      end }}\\n{{- end }}\\n{{- end }}\",\"details\":{\"parent_model\":\"\",\"format\":\"gguf\",\"family\":\"llama\",\"families\":[\"llama\"],\"parameter_size\":\"3.2B\",\"quantization_level\":\"Q4_K_M\"},\"model_info\":{\"general.architecture\":\"llama\",\"general.basename\":\"Llama-3.2\",\"general.file_type\":15,\"general.finetune\":\"Instruct\",\"general.languages\":[\"en\",\"de\",\"fr\",\"it\",\"pt\",\"hi\",\"es\",\"th\"],\"general.parameter_count\":3212749888,\"general.quantization_version\":2,\"general.size_label\":\"3B\",\"general.tags\":[\"facebook\",\"meta\",\"pytorch\",\"llama\",\"llama-3\",\"text-generation\"],\"general.type\":\"model\",\"llama.attention.head_count\":24,\"llama.attention.head_count_kv\":8,\"llama.attention.key_length\":128,\"llama.attention.layer_norm_rms_epsilon\":0.00001,\"llama.attention.value_length\":128,\"llama.block_count\":28,\"llama.context_length\":131072,\"llama.embedding_length\":3072,\"llama.feed_forward_length\":8192,\"llama.rope.dimension_count\":128,\"llama.rope.freq_base\":500000,\"llama.vocab_size\":128256,\"tokenizer.ggml.bos_token_id\":128000,\"tokenizer.ggml.eos_token_id\":128009,\"tokenizer.ggml.merges\":null,\"tokenizer.ggml.model\":\"gpt2\",\"tokenizer.ggml.pre\":\"llama-bpe\",\"tokenizer.ggml.token_type\":null,\"tokenizer.ggml.tokens\":null},\"modified_at\":\"2024-12-31T11:53:14.529771974-05:00\"}"
+    headers:
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Tue, 31 Dec 2024 17:00:06 GMT
+      Transfer-Encoding:
+      - chunked
+    http_version: HTTP/1.1
+    status_code: 200
 version: 1

tests/cli/tools/test_main.py

@@ -28,10 +28,9 @@ def test_create_success(mock_subprocess):
     with in_temp_dir():
         tool_command = ToolCommand()
 
-        with (
+        with patch.object(tool_command, "login") as mock_login, patch(
-            patch.object(tool_command, "login") as mock_login,
+            "sys.stdout", new=StringIO()
-            patch("sys.stdout", new=StringIO()) as fake_out,
+        ) as fake_out:
-        ):
             tool_command.create("test-tool")
             output = fake_out.getvalue()
 
@@ -83,7 +82,7 @@ def test_install_success(mock_get, mock_subprocess_run):
         capture_output=False,
         text=True,
         check=True,
-        env=unittest.mock.ANY,
+        env=unittest.mock.ANY
     )
 
     assert "Successfully installed sample-tool" in output

tests/crew_test.py

@@ -333,16 +333,16 @@ def test_manager_agent_delegating_to_assigned_task_agent():
     )
 
     mock_task_output = TaskOutput(
-        description="Mock description", raw="mocked output", agent="mocked agent"
+        description="Mock description",
+        raw="mocked output",
+        agent="mocked agent"
     )
 
     # Because we are mocking execute_sync, we never hit the underlying _execute_core
     # which sets the output attribute of the task
     task.output = mock_task_output
 
-    with patch.object(
+    with patch.object(Task, 'execute_sync', return_value=mock_task_output) as mock_execute_sync:
-        Task, "execute_sync", return_value=mock_task_output
-    ) as mock_execute_sync:
         crew.kickoff()
 
         # Verify execute_sync was called once
@@ -350,20 +350,12 @@ def test_manager_agent_delegating_to_assigned_task_agent():
 
         # Get the tools argument from the call
         _, kwargs = mock_execute_sync.call_args
-        tools = kwargs["tools"]
+        tools = kwargs['tools']
 
         # Verify the delegation tools were passed correctly
         assert len(tools) == 2
-        assert any(
+        assert any("Delegate a specific task to one of the following coworkers: Researcher" in tool.description for tool in tools)
-            "Delegate a specific task to one of the following coworkers: Researcher"
+        assert any("Ask a specific question to one of the following coworkers: Researcher" in tool.description for tool in tools)
-            in tool.description
-            for tool in tools
-        )
-        assert any(
-            "Ask a specific question to one of the following coworkers: Researcher"
-            in tool.description
-            for tool in tools
-        )
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -434,13 +426,13 @@ def test_manager_agent_delegates_with_varied_role_cases():
     )
 
     mock_task_output = TaskOutput(
-        description="Mock description", raw="mocked output", agent="mocked agent"
+        description="Mock description",
+        raw="mocked output",
+        agent="mocked agent"
     )
     task.output = mock_task_output
 
-    with patch.object(
+    with patch.object(Task, 'execute_sync', return_value=mock_task_output) as mock_execute_sync:
-        Task, "execute_sync", return_value=mock_task_output
-    ) as mock_execute_sync:
         crew.kickoff()
 
         # Verify execute_sync was called once
@@ -448,7 +440,7 @@ def test_manager_agent_delegates_with_varied_role_cases():
 
         # Get the tools argument from the call
         _, kwargs = mock_execute_sync.call_args
-        tools = kwargs["tools"]
+        tools = kwargs['tools']
 
         # Verify the delegation tools were passed correctly and can handle case/whitespace variations
         assert len(tools) == 2
@@ -457,23 +449,11 @@ def test_manager_agent_delegates_with_varied_role_cases():
         delegation_tool = tools[0]
         question_tool = tools[1]
         
-        assert (
+        assert "Delegate a specific task to one of the following coworkers:" in delegation_tool.description
-            "Delegate a specific task to one of the following coworkers:"
+        assert " Researcher " in delegation_tool.description or "SENIOR WRITER" in delegation_tool.description
-            in delegation_tool.description
-        )
-        assert (
-            " Researcher " in delegation_tool.description
-            or "SENIOR WRITER" in delegation_tool.description
-        )
         
-        assert (
+        assert "Ask a specific question to one of the following coworkers:" in question_tool.description
-            "Ask a specific question to one of the following coworkers:"
+        assert " Researcher " in question_tool.description or "SENIOR WRITER" in question_tool.description
-            in question_tool.description
-        )
-        assert (
-            " Researcher " in question_tool.description
-            or "SENIOR WRITER" in question_tool.description
-        )
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -499,7 +479,6 @@ def test_crew_with_delegating_agents():
         == "In the rapidly evolving landscape of technology, AI agents have emerged as formidable tools, revolutionizing how we interact with data and automate tasks. These sophisticated systems leverage machine learning and natural language processing to perform a myriad of functions, from virtual personal assistants to complex decision-making companions in industries such as finance, healthcare, and education. By mimicking human intelligence, AI agents can analyze massive data sets at unparalleled speeds, enabling businesses to uncover valuable insights, enhance productivity, and elevate user experiences to unprecedented levels.\n\nOne of the most striking aspects of AI agents is their adaptability; they learn from their interactions and continuously improve their performance over time. This feature is particularly valuable in customer service where AI agents can address inquiries, resolve issues, and provide personalized recommendations without the limitations of human fatigue. Moreover, with intuitive interfaces, AI agents enhance user interactions, making technology more accessible and user-friendly, thereby breaking down barriers that have historically hindered digital engagement.\n\nDespite their immense potential, the deployment of AI agents raises important ethical and practical considerations. Issues related to privacy, data security, and the potential for job displacement necessitate thoughtful dialogue and proactive measures. Striking a balance between technological innovation and societal impact will be crucial as organizations integrate these agents into their operations. Additionally, ensuring transparency in AI decision-making processes is vital to maintain public trust as AI agents become an integral part of daily life.\n\nLooking ahead, the future of AI agents appears bright, with ongoing advancements promising even greater capabilities. As we continue to harness the power of AI, we can expect these agents to play a transformative role in shaping various sectors—streamlining workflows, enabling smarter decision-making, and fostering more personalized experiences. Embracing this technology responsibly can lead to a future where AI agents not only augment human effort but also inspire creativity and efficiency across the board, ultimately redefining our interaction with the digital world."
     )
 
-
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_crew_with_delegating_agents_should_not_override_task_tools():
     from typing import Type
@@ -510,7 +489,6 @@ def test_crew_with_delegating_agents_should_not_override_task_tools():
 
     class TestToolInput(BaseModel):
         """Input schema for TestTool."""
-
         query: str = Field(..., description="Query to process")
 
     class TestTool(BaseTool):
@@ -538,29 +516,24 @@ def test_crew_with_delegating_agents_should_not_override_task_tools():
     )
 
     mock_task_output = TaskOutput(
-        description="Mock description", raw="mocked output", agent="mocked agent"
+        description="Mock description",
+        raw="mocked output",
+        agent="mocked agent"
     )
 
     # Because we are mocking execute_sync, we never hit the underlying _execute_core
     # which sets the output attribute of the task
     tasks[0].output = mock_task_output
 
-    with patch.object(
+    with patch.object(Task, 'execute_sync', return_value=mock_task_output) as mock_execute_sync:
-        Task, "execute_sync", return_value=mock_task_output
-    ) as mock_execute_sync:
         crew.kickoff()
 
         # Execute the task and verify both tools are present
         _, kwargs = mock_execute_sync.call_args
-        tools = kwargs["tools"]
+        tools = kwargs['tools']
-
-        assert any(
-            isinstance(tool, TestTool) for tool in tools
-        ), "TestTool should be present"
-        assert any(
-            "delegate" in tool.name.lower() for tool in tools
-        ), "Delegation tool should be present"
 
+        assert any(isinstance(tool, TestTool) for tool in tools), "TestTool should be present"
+        assert any("delegate" in tool.name.lower() for tool in tools), "Delegation tool should be present"
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_crew_with_delegating_agents_should_not_override_agent_tools():
@@ -572,7 +545,6 @@ def test_crew_with_delegating_agents_should_not_override_agent_tools():
 
     class TestToolInput(BaseModel):
         """Input schema for TestTool."""
-
         query: str = Field(..., description="Query to process")
 
     class TestTool(BaseTool):
@@ -591,7 +563,7 @@ def test_crew_with_delegating_agents_should_not_override_agent_tools():
         Task(
             description="Produce and amazing 1 paragraph draft of an article about AI Agents.",
             expected_output="A 4 paragraph article about AI.",
-            agent=new_ceo,
+            agent=new_ceo
         )
     ]
 
@@ -602,29 +574,24 @@ def test_crew_with_delegating_agents_should_not_override_agent_tools():
     )
 
     mock_task_output = TaskOutput(
-        description="Mock description", raw="mocked output", agent="mocked agent"
+        description="Mock description",
+        raw="mocked output",
+        agent="mocked agent"
     )
 
     # Because we are mocking execute_sync, we never hit the underlying _execute_core
     # which sets the output attribute of the task
     tasks[0].output = mock_task_output
 
-    with patch.object(
+    with patch.object(Task, 'execute_sync', return_value=mock_task_output) as mock_execute_sync:
-        Task, "execute_sync", return_value=mock_task_output
-    ) as mock_execute_sync:
         crew.kickoff()
 
         # Execute the task and verify both tools are present
         _, kwargs = mock_execute_sync.call_args
-        tools = kwargs["tools"]
+        tools = kwargs['tools']
-
-        assert any(
-            isinstance(tool, TestTool) for tool in new_ceo.tools
-        ), "TestTool should be present"
-        assert any(
-            "delegate" in tool.name.lower() for tool in tools
-        ), "Delegation tool should be present"
 
+        assert any(isinstance(tool, TestTool) for tool in new_ceo.tools), "TestTool should be present"
+        assert any("delegate" in tool.name.lower() for tool in tools), "Delegation tool should be present"
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_task_tools_override_agent_tools():
@@ -636,7 +603,6 @@ def test_task_tools_override_agent_tools():
 
     class TestToolInput(BaseModel):
         """Input schema for TestTool."""
-
         query: str = Field(..., description="Query to process")
 
     class TestTool(BaseTool):
@@ -664,10 +630,14 @@ def test_task_tools_override_agent_tools():
         description="Write a test task",
         expected_output="Test output",
         agent=new_researcher,
-        tools=[AnotherTestTool()],
+        tools=[AnotherTestTool()]
     )
 
-    crew = Crew(agents=[new_researcher], tasks=[task], process=Process.sequential)
+    crew = Crew(
+        agents=[new_researcher],
+        tasks=[task],
+        process=Process.sequential
+    )
 
     crew.kickoff()
 
@@ -680,7 +650,6 @@ def test_task_tools_override_agent_tools():
     assert len(new_researcher.tools) == 1
     assert isinstance(new_researcher.tools[0], TestTool)
 
-
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_task_tools_override_agent_tools_with_allow_delegation():
     """
@@ -733,13 +702,13 @@ def test_task_tools_override_agent_tools_with_allow_delegation():
     )
 
     mock_task_output = TaskOutput(
-        description="Mock description", raw="mocked output", agent="mocked agent"
+        description="Mock description",
+        raw="mocked output",
+        agent="mocked agent"
     )
 
     # We mock execute_sync to verify which tools get used at runtime
-    with patch.object(
+    with patch.object(Task, "execute_sync", return_value=mock_task_output) as mock_execute_sync:
-        Task, "execute_sync", return_value=mock_task_output
-    ) as mock_execute_sync:
         crew.kickoff()
 
         # Inspect the call kwargs to verify the actual tools passed to execution
@@ -747,23 +716,16 @@ def test_task_tools_override_agent_tools_with_allow_delegation():
         used_tools = kwargs["tools"]
 
         # Confirm AnotherTestTool is present but TestTool is not
-        assert any(
+        assert any(isinstance(tool, AnotherTestTool) for tool in used_tools), "AnotherTestTool should be present"
-            isinstance(tool, AnotherTestTool) for tool in used_tools
+        assert not any(isinstance(tool, TestTool) for tool in used_tools), "TestTool should not be present among used tools"
-        ), "AnotherTestTool should be present"
-        assert not any(
-            isinstance(tool, TestTool) for tool in used_tools
-        ), "TestTool should not be present among used tools"
 
         # Confirm delegation tool(s) are present
-        assert any(
+        assert any("delegate" in tool.name.lower() for tool in used_tools), "Delegation tool should be present"
-            "delegate" in tool.name.lower() for tool in used_tools
-        ), "Delegation tool should be present"
 
     # Finally, make sure the agent's original tools remain unchanged
     assert len(researcher_with_delegation.tools) == 1
     assert isinstance(researcher_with_delegation.tools[0], TestTool)
 
-
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_crew_verbose_output(capsys):
     tasks = [
@@ -1050,8 +1012,8 @@ def test_three_task_with_async_execution():
     )
 
 
-@pytest.mark.asyncio
 @pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.asyncio
 async def test_crew_async_kickoff():
     inputs = [
         {"topic": "dog"},
@@ -1098,9 +1060,8 @@ async def test_crew_async_kickoff():
             assert result[0].token_usage.successful_requests > 0  # type: ignore
 
 
-@pytest.mark.asyncio
 @pytest.mark.vcr(filter_headers=["authorization"])
-async def test_async_task_execution_call_count():
+def test_async_task_execution_call_count():
     from unittest.mock import MagicMock, patch
 
     list_ideas = Task(
@@ -1227,6 +1188,7 @@ def test_kickoff_for_each_empty_input():
     assert results == []
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
 def test_kickoff_for_each_invalid_input():
     """Tests if kickoff_for_each raises TypeError for invalid input types."""
 
@@ -1249,6 +1211,7 @@ def test_kickoff_for_each_invalid_input():
         crew.kickoff_for_each("invalid input")
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
 def test_kickoff_for_each_error_handling():
     """Tests error handling in kickoff_for_each when kickoff raises an error."""
     from unittest.mock import patch
@@ -1285,6 +1248,7 @@ def test_kickoff_for_each_error_handling():
             crew.kickoff_for_each(inputs=inputs)
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
 @pytest.mark.asyncio
 async def test_kickoff_async_basic_functionality_and_output():
     """Tests the basic functionality and output of kickoff_async."""
@@ -1319,6 +1283,7 @@ async def test_kickoff_async_basic_functionality_and_output():
         mock_kickoff.assert_called_once_with(inputs)
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
 @pytest.mark.asyncio
 async def test_async_kickoff_for_each_async_basic_functionality_and_output():
     """Tests the basic functionality and output of kickoff_for_each_async."""
@@ -1365,6 +1330,7 @@ async def test_async_kickoff_for_each_async_basic_functionality_and_output():
             mock_kickoff_async.assert_any_call(inputs=input_data)
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
 @pytest.mark.asyncio
 async def test_async_kickoff_for_each_async_empty_input():
     """Tests if akickoff_for_each_async handles an empty input list."""
@@ -1548,12 +1514,12 @@ def test_code_execution_flag_adds_code_tool_upon_kickoff():
     crew = Crew(agents=[programmer], tasks=[task])
 
     mock_task_output = TaskOutput(
-        description="Mock description", raw="mocked output", agent="mocked agent"
+        description="Mock description",
+        raw="mocked output",
+        agent="mocked agent"
     )
 
-    with patch.object(
+    with patch.object(Task, "execute_sync", return_value=mock_task_output) as mock_execute_sync:
-        Task, "execute_sync", return_value=mock_task_output
-    ) as mock_execute_sync:
         crew.kickoff()
 
         # Get the tools that were actually used in execution
@@ -1562,10 +1528,7 @@ def test_code_execution_flag_adds_code_tool_upon_kickoff():
 
         # Verify that exactly one tool was used and it was a CodeInterpreterTool
         assert len(used_tools) == 1, "Should have exactly one tool"
-        assert isinstance(
+        assert isinstance(used_tools[0], CodeInterpreterTool), "Tool should be CodeInterpreterTool"
-            used_tools[0], CodeInterpreterTool
-        ), "Tool should be CodeInterpreterTool"
-
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_delegation_is_not_enabled_if_there_are_only_one_agent():
@@ -1676,16 +1639,16 @@ def test_hierarchical_crew_creation_tasks_with_agents():
     )
 
     mock_task_output = TaskOutput(
-        description="Mock description", raw="mocked output", agent="mocked agent"
+        description="Mock description",
+        raw="mocked output",
+        agent="mocked agent"
     )
 
     # Because we are mocking execute_sync, we never hit the underlying _execute_core
     # which sets the output attribute of the task
     task.output = mock_task_output
 
-    with patch.object(
+    with patch.object(Task, 'execute_sync', return_value=mock_task_output) as mock_execute_sync:
-        Task, "execute_sync", return_value=mock_task_output
-    ) as mock_execute_sync:
         crew.kickoff()
 
         # Verify execute_sync was called once
@@ -1693,20 +1656,12 @@ def test_hierarchical_crew_creation_tasks_with_agents():
 
         # Get the tools argument from the call
         _, kwargs = mock_execute_sync.call_args
-        tools = kwargs["tools"]
+        tools = kwargs['tools']
 
         # Verify the delegation tools were passed correctly
         assert len(tools) == 2
-        assert any(
+        assert any("Delegate a specific task to one of the following coworkers: Senior Writer" in tool.description for tool in tools)
-            "Delegate a specific task to one of the following coworkers: Senior Writer"
+        assert any("Ask a specific question to one of the following coworkers: Senior Writer" in tool.description for tool in tools)
-            in tool.description
-            for tool in tools
-        )
-        assert any(
-            "Ask a specific question to one of the following coworkers: Senior Writer"
-            in tool.description
-            for tool in tools
-        )
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -1729,7 +1684,9 @@ def test_hierarchical_crew_creation_tasks_with_async_execution():
     )
 
     mock_task_output = TaskOutput(
-        description="Mock description", raw="mocked output", agent="mocked agent"
+        description="Mock description",
+        raw="mocked output",
+        agent="mocked agent"
     )
 
     # Create a mock Future that returns our TaskOutput
@@ -1740,9 +1697,7 @@ def test_hierarchical_crew_creation_tasks_with_async_execution():
     # which sets the output attribute of the task
     task.output = mock_task_output
 
-    with patch.object(
+    with patch.object(Task, 'execute_async', return_value=mock_future) as mock_execute_async:
-        Task, "execute_async", return_value=mock_future
-    ) as mock_execute_async:
         crew.kickoff()
 
         # Verify execute_async was called once
@@ -1750,20 +1705,12 @@ def test_hierarchical_crew_creation_tasks_with_async_execution():
 
         # Get the tools argument from the call
         _, kwargs = mock_execute_async.call_args
-        tools = kwargs["tools"]
+        tools = kwargs['tools']
 
         # Verify the delegation tools were passed correctly
         assert len(tools) == 2
-        assert any(
+        assert any("Delegate a specific task to one of the following coworkers: Senior Writer\n" in tool.description for tool in tools)
-            "Delegate a specific task to one of the following coworkers: Senior Writer\n"
+        assert any("Ask a specific question to one of the following coworkers: Senior Writer\n" in tool.description for tool in tools)
-            in tool.description
-            for tool in tools
-        )
-        assert any(
-            "Ask a specific question to one of the following coworkers: Senior Writer\n"
-            in tool.description
-            for tool in tools
-        )
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -2092,6 +2039,7 @@ def test_crew_output_file_end_to_end(tmp_path):
     assert expected_file.exists(), f"Output file {expected_file} was not created"
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
 def test_crew_output_file_validation_failures():
     """Test output file validation failures in a crew context."""
     agent = Agent(
@@ -2107,7 +2055,7 @@ def test_crew_output_file_validation_failures():
             description="Analyze data",
             expected_output="Analysis results",
             agent=agent,
-            output_file="../output.txt",
+            output_file="../output.txt"
         )
         Crew(agents=[agent], tasks=[task]).kickoff()
 
@@ -2117,7 +2065,7 @@ def test_crew_output_file_validation_failures():
             description="Analyze data",
             expected_output="Analysis results",
             agent=agent,
-            output_file="output.txt | rm -rf /",
+            output_file="output.txt | rm -rf /"
         )
         Crew(agents=[agent], tasks=[task]).kickoff()
 
@@ -2127,7 +2075,7 @@ def test_crew_output_file_validation_failures():
             description="Analyze data",
             expected_output="Analysis results",
             agent=agent,
-            output_file="~/output.txt",
+            output_file="~/output.txt"
         )
         Crew(agents=[agent], tasks=[task]).kickoff()
 
@@ -2137,11 +2085,12 @@ def test_crew_output_file_validation_failures():
             description="Analyze data",
             expected_output="Analysis results",
             agent=agent,
-            output_file="{invalid-name}/output.txt",
+            output_file="{invalid-name}/output.txt"
         )
         Crew(agents=[agent], tasks=[task]).kickoff()
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
 def test_manager_agent():
     from unittest.mock import patch
 
@@ -3100,7 +3049,6 @@ def test_task_tools_preserve_code_execution_tools():
 
     class TestToolInput(BaseModel):
         """Input schema for TestTool."""
-
         query: str = Field(..., description="Query to process")
 
     class TestTool(BaseTool):
@@ -3134,7 +3082,7 @@ def test_task_tools_preserve_code_execution_tools():
         description="Write a program to calculate fibonacci numbers.",
         expected_output="A working fibonacci calculator.",
         agent=programmer,
-        tools=[TestTool()],
+        tools=[TestTool()]
     )
 
     crew = Crew(
@@ -3144,12 +3092,12 @@ def test_task_tools_preserve_code_execution_tools():
     )
 
     mock_task_output = TaskOutput(
-        description="Mock description", raw="mocked output", agent="mocked agent"
+        description="Mock description",
+        raw="mocked output",
+        agent="mocked agent"
     )
 
-    with patch.object(
+    with patch.object(Task, "execute_sync", return_value=mock_task_output) as mock_execute_sync:
-        Task, "execute_sync", return_value=mock_task_output
-    ) as mock_execute_sync:
         crew.kickoff()
 
         # Get the tools that were actually used in execution
@@ -3157,21 +3105,12 @@ def test_task_tools_preserve_code_execution_tools():
         used_tools = kwargs["tools"]
 
         # Verify all expected tools are present
-        assert any(
+        assert any(isinstance(tool, TestTool) for tool in used_tools), "Task's TestTool should be present"
-            isinstance(tool, TestTool) for tool in used_tools
+        assert any(isinstance(tool, CodeInterpreterTool) for tool in used_tools), "CodeInterpreterTool should be present"
-        ), "Task's TestTool should be present"
+        assert any("delegate" in tool.name.lower() for tool in used_tools), "Delegation tool should be present"
-        assert any(
-            isinstance(tool, CodeInterpreterTool) for tool in used_tools
-        ), "CodeInterpreterTool should be present"
-        assert any(
-            "delegate" in tool.name.lower() for tool in used_tools
-        ), "Delegation tool should be present"
 
         # Verify the total number of tools (TestTool + CodeInterpreter + 2 delegation tools)
-        assert (
+        assert len(used_tools) == 4, "Should have TestTool, CodeInterpreter, and 2 delegation tools"
-            len(used_tools) == 4
-        ), "Should have TestTool, CodeInterpreter, and 2 delegation tools"
-
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_multimodal_flag_adds_multimodal_tools():
@@ -3200,13 +3139,13 @@ def test_multimodal_flag_adds_multimodal_tools():
     crew = Crew(agents=[multimodal_agent], tasks=[task], process=Process.sequential)
 
     mock_task_output = TaskOutput(
-        description="Mock description", raw="mocked output", agent="mocked agent"
+        description="Mock description",
+        raw="mocked output",
+        agent="mocked agent"
     )
 
     # Mock execute_sync to verify the tools passed at runtime
-    with patch.object(
+    with patch.object(Task, "execute_sync", return_value=mock_task_output) as mock_execute_sync:
-        Task, "execute_sync", return_value=mock_task_output
-    ) as mock_execute_sync:
         crew.kickoff()
 
         # Get the tools that were actually used in execution
@@ -3214,14 +3153,13 @@ def test_multimodal_flag_adds_multimodal_tools():
         used_tools = kwargs["tools"]
 
         # Check that the multimodal tool was added
-        assert any(
+        assert any(isinstance(tool, AddImageTool) for tool in used_tools), (
-            isinstance(tool, AddImageTool) for tool in used_tools
+            "AddImageTool should be present when agent is multimodal"
-        ), "AddImageTool should be present when agent is multimodal"
+        )
 
         # Verify we have exactly one tool (just the AddImageTool)
         assert len(used_tools) == 1, "Should only have the AddImageTool"
 
-
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_multimodal_agent_image_tool_handling():
     """
@@ -3263,10 +3201,10 @@ def test_multimodal_agent_image_tool_handling():
     mock_task_output = TaskOutput(
         description="Mock description",
         raw="A detailed analysis of the image",
-        agent="Image Analyst",
+        agent="Image Analyst"
     )
 
-    with patch.object(Task, "execute_sync") as mock_execute_sync:
+    with patch.object(Task, 'execute_sync') as mock_execute_sync:
         # Set up the mock to return our task output
         mock_execute_sync.return_value = mock_task_output
 
@@ -3275,7 +3213,7 @@ def test_multimodal_agent_image_tool_handling():
 
         # Get the tools that were passed to execute_sync
         _, kwargs = mock_execute_sync.call_args
-        tools = kwargs["tools"]
+        tools = kwargs['tools']
 
         # Verify the AddImageTool is present and properly configured
         image_tools = [tool for tool in tools if tool.name == "Add image to content"]
@@ -3285,7 +3223,7 @@ def test_multimodal_agent_image_tool_handling():
         image_tool = image_tools[0]
         result = image_tool._run(
             image_url="https://example.com/test-image.jpg",
-            action="Please analyze this image",
+            action="Please analyze this image"
         )
 
         # Verify the tool returns the expected format
@@ -3295,7 +3233,6 @@ def test_multimodal_agent_image_tool_handling():
         assert result["content"][0]["type"] == "text"
         assert result["content"][1]["type"] == "image_url"
 
-
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_multimodal_agent_live_image_analysis():
     """
@@ -3309,7 +3246,7 @@ def test_multimodal_agent_live_image_analysis():
         allow_delegation=False,
         multimodal=True,
         verbose=True,
-        llm="gpt-4o",
+        llm="gpt-4o"
     )
 
     # Create a task for image analysis
@@ -3320,18 +3257,19 @@ def test_multimodal_agent_live_image_analysis():
         Image: {image_url}
         """,
         expected_output="A comprehensive description of the image contents.",
-        agent=image_analyst,
+        agent=image_analyst
     )
 
     # Create and run the crew
-    crew = Crew(agents=[image_analyst], tasks=[analyze_image])
+    crew = Crew(
+        agents=[image_analyst],
+        tasks=[analyze_image]
+    )
 
     # Execute with an image URL
-    result = crew.kickoff(
+    result = crew.kickoff(inputs={
-        inputs={
+        "image_url": "https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k="
-            "image_url": "https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k="
+    })
-        }
-    )
 
     # Verify we got a meaningful response
     assert isinstance(result.raw, str)

tests/knowledge/knowledge_test.py

@@ -578,6 +578,14 @@ def test_multiple_docling_sources():
     assert docling_source.content is not None
 
 
+def test_docling_source_with_local_file():
+    current_dir = Path(__file__).parent
+    pdf_path = current_dir / "crewai_quickstart.pdf"
+    docling_source = CrewDoclingSource(file_paths=[pdf_path])
+    assert docling_source.file_paths == [pdf_path]
+    assert docling_source.content is not None
+
+
 def test_file_path_validation():
     """Test file path validation for knowledge sources."""
     current_dir = Path(__file__).parent
@@ -598,6 +606,6 @@ def test_file_path_validation():
     # Test neither file_path nor file_paths provided
     with pytest.raises(
         ValueError,
-        match="file_path/file_paths must be a Path, str, or a list of these types",
+        match="file_path/file_paths must be a Path, str, or a list of these types"
     ):
         PDFKnowledgeSource()

tests/task_test.py

@@ -719,7 +719,7 @@ def test_interpolate_inputs():
     task = Task(
         description="Give me a list of 5 interesting ideas about {topic} to explore for an article, what makes them unique and interesting.",
         expected_output="Bullet point list of 5 interesting ideas about {topic}.",
-        output_file="/tmp/{topic}/output_{date}.txt",
+        output_file="/tmp/{topic}/output_{date}.txt"
     )
 
     task.interpolate_inputs(inputs={"topic": "AI", "date": "2024"})
@@ -742,14 +742,15 @@ def test_interpolate_inputs():
 def test_interpolate_only():
     """Test the interpolate_only method for various scenarios including JSON structure preservation."""
     task = Task(
-        description="Unused in this test", expected_output="Unused in this test"
+        description="Unused in this test",
+        expected_output="Unused in this test"
     )
     
     # Test JSON structure preservation
     json_string = '{"info": "Look at {placeholder}", "nested": {"val": "{nestedVal}"}}'
     result = task.interpolate_only(
         input_string=json_string,
-        inputs={"placeholder": "the data", "nestedVal": "something else"},
+        inputs={"placeholder": "the data", "nestedVal": "something else"}
     )
     assert '"info": "Look at the data"' in result
     assert '"val": "something else"' in result
@@ -759,18 +760,23 @@ def test_interpolate_only():
     # Test normal string interpolation
     normal_string = "Hello {name}, welcome to {place}!"
     result = task.interpolate_only(
-        input_string=normal_string, inputs={"name": "John", "place": "CrewAI"}
+        input_string=normal_string,
+        inputs={"name": "John", "place": "CrewAI"}
     )
     assert result == "Hello John, welcome to CrewAI!"
     
     # Test empty string
-    result = task.interpolate_only(input_string="", inputs={"unused": "value"})
+    result = task.interpolate_only(
+        input_string="",
+        inputs={"unused": "value"}
+    )
     assert result == ""
     
     # Test string with no placeholders
     no_placeholders = "Hello, this is a test"
     result = task.interpolate_only(
-        input_string=no_placeholders, inputs={"unused": "value"}
+        input_string=no_placeholders,
+        inputs={"unused": "value"}
     )
     assert result == no_placeholders
 
@@ -874,65 +880,56 @@ def test_key():
 def test_output_file_validation():
     """Test output file path validation."""
     # Valid paths
-    assert (
+    assert Task(
-        Task(
+        description="Test task",
-            description="Test task",
+        expected_output="Test output",
-            expected_output="Test output",
+        output_file="output.txt"
-            output_file="output.txt",
+    ).output_file == "output.txt"
-        ).output_file
+    assert Task(
-        == "output.txt"
+        description="Test task",
-    )
+        expected_output="Test output",
-    assert (
+        output_file="/tmp/output.txt"
-        Task(
+    ).output_file == "tmp/output.txt"
-            description="Test task",
+    assert Task(
-            expected_output="Test output",
+        description="Test task",
-            output_file="/tmp/output.txt",
+        expected_output="Test output",
-        ).output_file
+        output_file="{dir}/output_{date}.txt"
-        == "tmp/output.txt"
+    ).output_file == "{dir}/output_{date}.txt"
-    )
-    assert (
-        Task(
-            description="Test task",
-            expected_output="Test output",
-            output_file="{dir}/output_{date}.txt",
-        ).output_file
-        == "{dir}/output_{date}.txt"
-    )
     
     # Invalid paths
     with pytest.raises(ValueError, match="Path traversal"):
         Task(
             description="Test task",
             expected_output="Test output",
-            output_file="../output.txt",
+            output_file="../output.txt"
         )
     with pytest.raises(ValueError, match="Path traversal"):
         Task(
             description="Test task",
             expected_output="Test output",
-            output_file="folder/../output.txt",
+            output_file="folder/../output.txt"
         )
     with pytest.raises(ValueError, match="Shell special characters"):
         Task(
             description="Test task",
             expected_output="Test output",
-            output_file="output.txt | rm -rf /",
+            output_file="output.txt | rm -rf /"
         )
     with pytest.raises(ValueError, match="Shell expansion"):
         Task(
             description="Test task",
             expected_output="Test output",
-            output_file="~/output.txt",
+            output_file="~/output.txt"
         )
     with pytest.raises(ValueError, match="Shell expansion"):
         Task(
             description="Test task",
             expected_output="Test output",
-            output_file="$HOME/output.txt",
+            output_file="$HOME/output.txt"
         )
     with pytest.raises(ValueError, match="Invalid template variable"):
         Task(
             description="Test task",
             expected_output="Test output",
-            output_file="{invalid-name}/output.txt",
+            output_file="{invalid-name}/output.txt"
         )

tests/test_manager_llm_delegation.py

@@ -8,49 +8,48 @@ from crewai.tools.agent_tools.base_agent_tools import BaseAgentTool
 
 class TestAgentTool(BaseAgentTool):
     """Concrete implementation of BaseAgentTool for testing."""
-
     def _run(self, *args, **kwargs):
         """Implement required _run method."""
         return "Test response"
 
-
+@pytest.mark.parametrize("role_name,should_match", [
-@pytest.mark.parametrize(
+    ('Futel Official Infopoint', True),                    # exact match
-    "role_name,should_match",
+    ('  "Futel Official Infopoint"  ', True),             # extra quotes and spaces
-    [
+    ('Futel Official Infopoint\n', True),                 # trailing newline
-        ("Futel Official Infopoint", True),  # exact match
+    ('"Futel Official Infopoint"', True),                 # embedded quotes
-        ('  "Futel Official Infopoint"  ', True),  # extra quotes and spaces
+    (' FUTEL\nOFFICIAL   INFOPOINT ', True),             # multiple whitespace and newline
-        ("Futel Official Infopoint\n", True),  # trailing newline
+    ('futel official infopoint', True),                   # lowercase
-        ('"Futel Official Infopoint"', True),  # embedded quotes
+    ('FUTEL OFFICIAL INFOPOINT', True),                   # uppercase
-        (" FUTEL\nOFFICIAL   INFOPOINT ", True),  # multiple whitespace and newline
+    ('Non Existent Agent', False),                        # non-existent agent
-        ("futel official infopoint", True),  # lowercase
+    (None, False),                                        # None agent name
-        ("FUTEL OFFICIAL INFOPOINT", True),  # uppercase
+])
-        ("Non Existent Agent", False),  # non-existent agent
-        (None, False),  # None agent name
-    ],
-)
 def test_agent_tool_role_matching(role_name, should_match):
     """Test that agent tools can match roles regardless of case, whitespace, and special characters."""
     # Create test agent
     test_agent = Agent(
-        role="Futel Official Infopoint",
+        role='Futel Official Infopoint',
-        goal="Answer questions about Futel",
+        goal='Answer questions about Futel',
-        backstory="Futel Football Club info",
+        backstory='Futel Football Club info',
-        allow_delegation=False,
+        allow_delegation=False
     )
 
     # Create test agent tool
     agent_tool = TestAgentTool(
-        name="test_tool", description="Test tool", agents=[test_agent]
+        name="test_tool",
+        description="Test tool",
+        agents=[test_agent]
     )
 
     # Test role matching
-    result = agent_tool._execute(agent_name=role_name, task="Test task", context=None)
+    result = agent_tool._execute(
+        agent_name=role_name,
+        task='Test task',
+        context=None
+    )
 
     if should_match:
-        assert (
+        assert "coworker mentioned not found" not in result.lower(), \
-            "coworker mentioned not found" not in result.lower()
+            f"Should find agent with role name: {role_name}"
-        ), f"Should find agent with role name: {role_name}"
     else:
-        assert (
+        assert "coworker mentioned not found" in result.lower(), \
-            "coworker mentioned not found" in result.lower()
+            f"Should not find agent with role name: {role_name}"
-        ), f"Should not find agent with role name: {role_name}"

tests/test_task_guardrails.py

@@ -15,7 +15,10 @@ def test_task_without_guardrail():
     agent.execute_task.return_value = "test result"
     agent.crew = None
 
-    task = Task(description="Test task", expected_output="Output")
+    task = Task(
+        description="Test task",
+        expected_output="Output"
+    )
 
     result = task.execute_sync(agent=agent)
     assert isinstance(result, TaskOutput)
@@ -24,7 +27,6 @@ def test_task_without_guardrail():
 
 def test_task_with_successful_guardrail():
     """Test that successful guardrail validation passes transformed result."""
-
     def guardrail(result: TaskOutput):
         return (True, result.raw.upper())
 
@@ -33,7 +35,11 @@ def test_task_with_successful_guardrail():
     agent.execute_task.return_value = "test result"
     agent.crew = None
 
-    task = Task(description="Test task", expected_output="Output", guardrail=guardrail)
+    task = Task(
+        description="Test task",
+        expected_output="Output",
+        guardrail=guardrail
+    )
 
     result = task.execute_sync(agent=agent)
     assert isinstance(result, TaskOutput)
@@ -42,20 +48,22 @@ def test_task_with_successful_guardrail():
 
 def test_task_with_failing_guardrail():
     """Test that failing guardrail triggers retry with error context."""
-
     def guardrail(result: TaskOutput):
         return (False, "Invalid format")
 
     agent = Mock()
     agent.role = "test_agent"
-    agent.execute_task.side_effect = ["bad result", "good result"]
+    agent.execute_task.side_effect = [
+        "bad result",
+        "good result"
+    ]
     agent.crew = None
 
     task = Task(
         description="Test task",
         expected_output="Output",
         guardrail=guardrail,
-        max_retries=1,
+        max_retries=1
     )
 
     # First execution fails guardrail, second succeeds
@@ -69,7 +77,6 @@ def test_task_with_failing_guardrail():
 
 def test_task_with_guardrail_retries():
     """Test that guardrail respects max_retries configuration."""
-
     def guardrail(result: TaskOutput):
         return (False, "Invalid format")
 
@@ -82,7 +89,7 @@ def test_task_with_guardrail_retries():
         description="Test task",
         expected_output="Output",
         guardrail=guardrail,
-        max_retries=2,
+        max_retries=2
     )
 
     with pytest.raises(Exception) as exc_info:
@@ -95,7 +102,6 @@ def test_task_with_guardrail_retries():
 
 def test_guardrail_error_in_context():
     """Test that guardrail error is passed in context for retry."""
-
     def guardrail(result: TaskOutput):
         return (False, "Expected JSON, got string")
 
@@ -107,12 +113,11 @@ def test_guardrail_error_in_context():
         description="Test task",
         expected_output="Output",
         guardrail=guardrail,
-        max_retries=1,
+        max_retries=1
     )
 
     # Mock execute_task to succeed on second attempt
     first_call = True
-
     def execute_task(task, context, tools):
         nonlocal first_call
         if first_call:

uv.lock

@@ -1,18 +1,18 @@
 version = 1
 requires-python = ">=3.10, <3.13"
 resolution-markers = [
-    "python_full_version < '3.11' and sys_platform == 'darwin'",
+    "python_full_version < '3.11' and platform_system == 'Darwin'",
-    "python_full_version < '3.11' and platform_machine == 'aarch64' and sys_platform == 'linux'",
+    "python_full_version < '3.11' and platform_machine == 'aarch64' and platform_system == 'Linux'",
-    "(python_full_version < '3.11' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version < '3.11' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "(python_full_version < '3.11' and platform_machine != 'aarch64' and platform_system != 'Darwin') or (python_full_version < '3.11' and platform_system != 'Darwin' and platform_system != 'Linux')",
-    "python_full_version == '3.11.*' and sys_platform == 'darwin'",
+    "python_full_version == '3.11.*' and platform_system == 'Darwin'",
-    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and sys_platform == 'linux'",
+    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and platform_system == 'Linux'",
-    "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version == '3.11.*' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and platform_system != 'Darwin') or (python_full_version == '3.11.*' and platform_system != 'Darwin' and platform_system != 'Linux')",
-    "python_full_version >= '3.12' and python_full_version < '3.12.4' and sys_platform == 'darwin'",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_system == 'Darwin'",
-    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and sys_platform == 'linux'",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Linux'",
-    "(python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.12' and python_full_version < '3.12.4' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "(python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine != 'aarch64' and platform_system != 'Darwin') or (python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_system != 'Darwin' and platform_system != 'Linux')",
-    "python_full_version >= '3.12.4' and sys_platform == 'darwin'",
+    "python_full_version >= '3.12.4' and platform_system == 'Darwin'",
-    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and sys_platform == 'linux'",
+    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Linux'",
-    "(python_full_version >= '3.12.4' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.12.4' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "(python_full_version >= '3.12.4' and platform_machine != 'aarch64' and platform_system != 'Darwin') or (python_full_version >= '3.12.4' and platform_system != 'Darwin' and platform_system != 'Linux')",
 ]
 
 [[package]]
@@ -683,7 +683,7 @@ requires-dist = [
     { name = "instructor", specifier = ">=1.3.3" },
     { name = "json-repair", specifier = ">=0.25.2" },
     { name = "jsonref", specifier = ">=1.1.0" },
-    { name = "litellm", specifier = ">=1.44.22" },
+    { name = "litellm", specifier = ">=1.56.4" },
     { name = "mem0ai", marker = "extra == 'mem0'", specifier = ">=0.1.29" },
     { name = "openai", specifier = ">=1.13.3" },
     { name = "openpyxl", specifier = ">=3.1.5" },
@@ -2229,24 +2229,24 @@ wheels = [
 
 [[package]]
 name = "litellm"
-version = "1.50.2"
+version = "1.56.4"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "aiohttp" },
     { name = "click" },
+    { name = "httpx" },
     { name = "importlib-metadata" },
     { name = "jinja2" },
     { name = "jsonschema" },
     { name = "openai" },
     { name = "pydantic" },
     { name = "python-dotenv" },
-    { name = "requests" },
     { name = "tiktoken" },
     { name = "tokenizers" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/a7/45/4d54617b267a96f1f7c17c0010ea1aba20e30a3672b873fe92a6001e5952/litellm-1.50.2.tar.gz", hash = "sha256:b244c9a0e069cc626b85fb9f5cc252114aaff1225500da30ce0940f841aef8ea", size = 6096949 }
+sdist = { url = "https://files.pythonhosted.org/packages/83/ea/2c51d16c244a64dd3f0bdb1757aef798cf943b92e5695da04e3e42ba09e0/litellm-1.56.4.tar.gz", hash = "sha256:2808ca21878d200f7676a3d11e5bf2b5e3349ae504628f279cd7297c7dbd2038", size = 6284983 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/22/f3/89a4d65d1b9286eb5ac6a6e92dd93523d92f3142a832e60c00d5cad64176/litellm-1.50.2-py3-none-any.whl", hash = "sha256:99cac60c78037946ab809b7cfbbadad53507bb2db8ae39391b4be215a0869fdd", size = 6318265 },
+    { url = "https://files.pythonhosted.org/packages/8f/25/2fd7b28a270b2963e8fa0ecf6aab4db47c54d932cc5aac8bc87e7ebc3755/litellm-1.56.4-py3-none-any.whl", hash = "sha256:699a8db46f7de045069a77c435e13244b5fdaf5df1c8cb5e6ad675ef7e104ccd", size = 6564370 },
 ]
 
 [[package]]
@@ -2900,7 +2900,7 @@ name = "nvidia-cudnn-cu12"
 version = "9.1.0.70"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
+    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/9f/fd/713452cd72343f682b1c7b9321e23829f00b842ceaedcda96e742ea0b0b3/nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl", hash = "sha256:165764f44ef8c61fcdfdfdbe769d687e06374059fbb388b6c89ecb0e28793a6f", size = 664752741 },
@@ -2927,9 +2927,9 @@ name = "nvidia-cusolver-cu12"
 version = "11.4.5.107"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
+    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" },
-    { name = "nvidia-cusparse-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
+    { name = "nvidia-cusparse-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" },
-    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
+    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/bc/1d/8de1e5c67099015c834315e333911273a8c6aaba78923dd1d1e25fc5f217/nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl", hash = "sha256:8a7ec542f0412294b15072fa7dab71d31334014a69f953004ea7a118206fe0dd", size = 124161928 },
@@ -2940,7 +2940,7 @@ name = "nvidia-cusparse-cu12"
 version = "12.1.0.106"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
+    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/65/5b/cfaeebf25cd9fdec14338ccb16f6b2c4c7fa9163aefcf057d86b9cc248bb/nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:f3b50f42cf363f86ab21f720998517a659a48131e8d538dc02f8768237bd884c", size = 195958278 },
@@ -3040,7 +3040,7 @@ wheels = [
 
 [[package]]
 name = "openai"
-version = "1.52.1"
+version = "1.58.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "anyio" },
@@ -3052,9 +3052,9 @@ dependencies = [
     { name = "tqdm" },
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/80/ac/54c76352d493866637756b7c0ecec44f0b5bafb8fe753d98472cf6cfe4ce/openai-1.52.1.tar.gz", hash = "sha256:383b96c7e937cbec23cad5bf5718085381e4313ca33c5c5896b54f8e1b19d144", size = 310069 }
+sdist = { url = "https://files.pythonhosted.org/packages/27/3c/b1ecce430ed56fa3ac1b0676966d3250aab9c70a408232b71e419ea62148/openai-1.58.1.tar.gz", hash = "sha256:f5a035fd01e141fc743f4b0e02c41ca49be8fab0866d3b67f5f29b4f4d3c0973", size = 343411 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/ad/31/28a83e124e9f9dd04c83b5aeb6f8b1770f45addde4dd3d34d9a9091590ad/openai-1.52.1-py3-none-any.whl", hash = "sha256:f23e83df5ba04ee0e82c8562571e8cb596cd88f9a84ab783e6c6259e5ffbfb4a", size = 386945 },
+    { url = "https://files.pythonhosted.org/packages/8e/5a/d22cd07f1a99b9e8b3c92ee0c1959188db4318828a3d88c9daac120bdd69/openai-1.58.1-py3-none-any.whl", hash = "sha256:e2910b1170a6b7f88ef491ac3a42c387f08bd3db533411f7ee391d166571d63c", size = 454279 },
 ]
 
 [[package]]
@@ -5165,7 +5165,7 @@ name = "triton"
 version = "3.0.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "filelock", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
+    { name = "filelock", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/45/27/14cc3101409b9b4b9241d2ba7deaa93535a217a211c86c4cc7151fb12181/triton-3.0.0-1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e1efef76935b2febc365bfadf74bcb65a6f959a9872e5bddf44cc9e0adce1e1a", size = 209376304 },