mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-09 08:08:32 +00:00
Fix nested pydantic model issue (#1905)
* Fix nested pydantic model issue * fix failing tests * add in vcr * cleanup * drop prints * Fix vcr issues * added new recordings * trying to fix vcr * add in fix from lorenze.
This commit is contained in:
Brandon Hancock (bhancock_ai)
committed by
GitHub
GitHub
parent
42311d9c7a
commit
b5779dca12
114
tests/utilities/cassettes/test_convert_with_instructions.yaml
Normal file
114
tests/utilities/cassettes/test_convert_with_instructions.yaml
Normal file
@@ -0,0 +1,114 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: '{"messages": [{"role": "user", "content": "Name: Alice, Age: 30"}], "model":
|
||||
"gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name": "SimpleModel"}},
|
||||
"tools": [{"type": "function", "function": {"name": "SimpleModel", "description":
|
||||
"Correctly extracted `SimpleModel` with all the required parameters with correct
|
||||
types", "parameters": {"properties": {"name": {"title": "Name", "type": "string"},
|
||||
"age": {"title": "Age", "type": "integer"}}, "required": ["age", "name"], "type":
|
||||
"object"}}}]}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '507'
|
||||
content-type:
|
||||
- application/json
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.59.6
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.59.6
|
||||
x-stainless-raw-response:
|
||||
- 'true'
|
||||
x-stainless-retry-count:
|
||||
- '0'
|
||||
x-stainless-runtime:
|
||||
- CPython
|
||||
x-stainless-runtime-version:
|
||||
- 3.12.7
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
content: "{\n \"id\": \"chatcmpl-Aq4a4xDv8G0i4fbTtPJEI2B8UNBup\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1736974028,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
|
||||
\ \"id\": \"call_uO5nec8hTk1fpYINM8TUafhe\",\n \"type\":
|
||||
\"function\",\n \"function\": {\n \"name\": \"SimpleModel\",\n
|
||||
\ \"arguments\": \"{\\\"name\\\":\\\"Alice\\\",\\\"age\\\":30}\"\n
|
||||
\ }\n }\n ],\n \"refusal\": null\n },\n
|
||||
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
|
||||
\ \"usage\": {\n \"prompt_tokens\": 79,\n \"completion_tokens\": 10,\n
|
||||
\ \"total_tokens\": 89,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
|
||||
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
|
||||
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
|
||||
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
|
||||
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 9028b81aeb1cb05f-ATL
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Wed, 15 Jan 2025 20:47:08 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Set-Cookie:
|
||||
- __cf_bm=PzayZLF04c14veGc.0ocVg3VHBbpzKRW8Hqox8L9U7c-1736974028-1.0.1.1-mZpK8.SH9l7K2z8Tvt6z.dURiVPjFqEz7zYEITfRwdr5z0razsSebZGN9IRPmI5XC_w5rbZW2Kg6hh5cenXinQ;
|
||||
path=/; expires=Wed, 15-Jan-25 21:17:08 GMT; domain=.api.openai.com; HttpOnly;
|
||||
Secure; SameSite=None
|
||||
- _cfuvid=ciwC3n2Srn20xx4JhEUeN6Ap0tNBaE44S95nIilboQ0-1736974028496-0.0.1.1-604800000;
|
||||
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
X-Content-Type-Options:
|
||||
- nosniff
|
||||
access-control-expose-headers:
|
||||
- X-Request-ID
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400
|
||||
openai-organization:
|
||||
- crewai-iuxna1
|
||||
openai-processing-ms:
|
||||
- '439'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
x-ratelimit-limit-requests:
|
||||
- '30000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '150000000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '29999'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '149999978'
|
||||
x-ratelimit-reset-requests:
|
||||
- 2ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 0s
|
||||
x-request-id:
|
||||
- req_a468000458b9d2848b7497b2e3d485a3
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
version: 1
|
||||
2048
tests/utilities/cassettes/test_converter_with_llama3_1_model.yaml
Normal file
2048
tests/utilities/cassettes/test_converter_with_llama3_1_model.yaml
Normal file
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,869 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: '{"model": "llama3.2:3b", "prompt": "### User:\nName: Alice Llama, Age:
|
||||
30\n\n### System:\nProduce JSON OUTPUT ONLY! Adhere to this format {\"name\":
|
||||
\"function_name\", \"arguments\":{\"argument_name\": \"argument_value\"}} The
|
||||
following functions are available to you:\n{''type'': ''function'', ''function'':
|
||||
{''name'': ''SimpleModel'', ''description'': ''Correctly extracted `SimpleModel`
|
||||
with all the required parameters with correct types'', ''parameters'': {''properties'':
|
||||
{''name'': {''title'': ''Name'', ''type'': ''string''}, ''age'': {''title'':
|
||||
''Age'', ''type'': ''integer''}}, ''required'': [''age'', ''name''], ''type'':
|
||||
''object''}}}\n\n\n", "options": {}, "stream": false, "format": "json"}'
|
||||
headers:
|
||||
accept:
|
||||
- '*/*'
|
||||
accept-encoding:
|
||||
- gzip, deflate
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '657'
|
||||
host:
|
||||
- localhost:11434
|
||||
user-agent:
|
||||
- litellm/1.57.4
|
||||
method: POST
|
||||
uri: http://localhost:11434/api/generate
|
||||
response:
|
||||
content: '{"model":"llama3.2:3b","created_at":"2025-01-15T20:47:11.926411Z","response":"{\"name\":
|
||||
\"SimpleModel\", \"arguments\":{\"name\": \"Alice Llama\", \"age\": 30}}","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,2724,512,678,25,30505,445,81101,11,13381,25,220,966,271,14711,744,512,1360,13677,4823,32090,27785,0,2467,6881,311,420,3645,5324,609,794,330,1723,1292,498,330,16774,23118,14819,1292,794,330,14819,3220,32075,578,2768,5865,527,2561,311,499,512,13922,1337,1232,364,1723,518,364,1723,1232,5473,609,1232,364,16778,1747,518,364,4789,1232,364,34192,398,28532,1595,16778,1747,63,449,682,279,2631,5137,449,4495,4595,518,364,14105,1232,5473,13495,1232,5473,609,1232,5473,2150,1232,364,678,518,364,1337,1232,364,928,25762,364,425,1232,5473,2150,1232,364,17166,518,364,1337,1232,364,11924,8439,2186,364,6413,1232,2570,425,518,364,609,4181,364,1337,1232,364,1735,23742,3818,128009,128006,78191,128007,271,5018,609,794,330,16778,1747,498,330,16774,23118,609,794,330,62786,445,81101,498,330,425,794,220,966,3500],"total_duration":3374470708,"load_duration":1075750500,"prompt_eval_count":167,"prompt_eval_duration":1871000000,"eval_count":24,"eval_duration":426000000}'
|
||||
headers:
|
||||
Content-Length:
|
||||
- '1263'
|
||||
Content-Type:
|
||||
- application/json; charset=utf-8
|
||||
Date:
|
||||
- Wed, 15 Jan 2025 20:47:12 GMT
|
||||
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/1.57.4
|
||||
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:
|
||||
- Wed, 15 Jan 2025 20:47:12 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/1.57.4
|
||||
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:
|
||||
- Wed, 15 Jan 2025 20:47:12 GMT
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
version: 1
|
||||
116
tests/utilities/cassettes/test_converter_with_nested_model.yaml
Normal file
116
tests/utilities/cassettes/test_converter_with_nested_model.yaml
Normal file
@@ -0,0 +1,116 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: '{"messages": [{"role": "user", "content": "Name: John Doe\nAge: 30\nAddress:
|
||||
123 Main St, Anytown, 12345"}], "model": "gpt-4o-mini", "tool_choice": {"type":
|
||||
"function", "function": {"name": "Person"}}, "tools": [{"type": "function",
|
||||
"function": {"name": "Person", "description": "Correctly extracted `Person`
|
||||
with all the required parameters with correct types", "parameters": {"$defs":
|
||||
{"Address": {"properties": {"street": {"title": "Street", "type": "string"},
|
||||
"city": {"title": "City", "type": "string"}, "zip_code": {"title": "Zip Code",
|
||||
"type": "string"}}, "required": ["street", "city", "zip_code"], "title": "Address",
|
||||
"type": "object"}}, "properties": {"name": {"title": "Name", "type": "string"},
|
||||
"age": {"title": "Age", "type": "integer"}, "address": {"$ref": "#/$defs/Address"}},
|
||||
"required": ["address", "age", "name"], "type": "object"}}}]}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '853'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- __cf_bm=PzayZLF04c14veGc.0ocVg3VHBbpzKRW8Hqox8L9U7c-1736974028-1.0.1.1-mZpK8.SH9l7K2z8Tvt6z.dURiVPjFqEz7zYEITfRwdr5z0razsSebZGN9IRPmI5XC_w5rbZW2Kg6hh5cenXinQ;
|
||||
_cfuvid=ciwC3n2Srn20xx4JhEUeN6Ap0tNBaE44S95nIilboQ0-1736974028496-0.0.1.1-604800000
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.59.6
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.59.6
|
||||
x-stainless-raw-response:
|
||||
- 'true'
|
||||
x-stainless-retry-count:
|
||||
- '0'
|
||||
x-stainless-runtime:
|
||||
- CPython
|
||||
x-stainless-runtime-version:
|
||||
- 3.12.7
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
content: "{\n \"id\": \"chatcmpl-Aq4aFpbhU10QK0e6Jlkxy8AUxCZCf\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1736974039,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
|
||||
\ \"id\": \"call_N29aoGL9tN0qL2O7HI8Op2so\",\n \"type\":
|
||||
\"function\",\n \"function\": {\n \"name\": \"Person\",\n
|
||||
\ \"arguments\": \"{\\\"name\\\":\\\"John Doe\\\",\\\"age\\\":30,\\\"address\\\":{\\\"street\\\":\\\"123
|
||||
Main St\\\",\\\"city\\\":\\\"Anytown\\\",\\\"zip_code\\\":\\\"12345\\\"}}\"\n
|
||||
\ }\n }\n ],\n \"refusal\": null\n },\n
|
||||
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
|
||||
\ \"usage\": {\n \"prompt_tokens\": 118,\n \"completion_tokens\": 30,\n
|
||||
\ \"total_tokens\": 148,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
|
||||
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
|
||||
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
|
||||
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
|
||||
\"default\",\n \"system_fingerprint\": \"fp_bd83329f63\"\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 9028b863dbaa672f-ATL
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Wed, 15 Jan 2025 20:47:20 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
X-Content-Type-Options:
|
||||
- nosniff
|
||||
access-control-expose-headers:
|
||||
- X-Request-ID
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400
|
||||
openai-organization:
|
||||
- crewai-iuxna1
|
||||
openai-processing-ms:
|
||||
- '840'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
x-ratelimit-limit-requests:
|
||||
- '30000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '150000000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '29999'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '149999968'
|
||||
x-ratelimit-reset-requests:
|
||||
- 2ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 0s
|
||||
x-request-id:
|
||||
- req_2f9d1e3f0ace4944891dde05093486aa
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
version: 1
|
||||
@@ -39,6 +39,22 @@ class NestedModel(BaseModel):
|
||||
data: SimpleModel
|
||||
|
||||
|
||||
class Address(BaseModel):
|
||||
street: str
|
||||
city: str
|
||||
zip_code: str
|
||||
|
||||
|
||||
class Person(BaseModel):
|
||||
name: str
|
||||
age: int
|
||||
address: Address
|
||||
|
||||
|
||||
class CustomConverter(Converter):
|
||||
pass
|
||||
|
||||
|
||||
# Fixtures
|
||||
@pytest.fixture
|
||||
def mock_agent():
|
||||
@@ -199,26 +215,23 @@ def test_convert_with_instructions_failure(
|
||||
|
||||
# Tests for get_conversion_instructions
|
||||
def test_get_conversion_instructions_gpt():
|
||||
mock_llm = Mock()
|
||||
mock_llm.openai_api_base = None
|
||||
llm = LLM(model="gpt-4o-mini")
|
||||
with patch.object(LLM, "supports_function_calling") as supports_function_calling:
|
||||
supports_function_calling.return_value = True
|
||||
instructions = get_conversion_instructions(SimpleModel, mock_llm)
|
||||
instructions = get_conversion_instructions(SimpleModel, llm)
|
||||
model_schema = PydanticSchemaParser(model=SimpleModel).get_schema()
|
||||
assert (
|
||||
instructions
|
||||
== f"I'm gonna convert this raw text into valid JSON.\n\nThe json should have the following structure, with the following keys:\n{model_schema}"
|
||||
== f"Please convert the following text into valid JSON.\n\nThe JSON should follow this schema:\n```json\n{model_schema}\n```"
|
||||
)
|
||||
|
||||
|
||||
def test_get_conversion_instructions_non_gpt():
|
||||
mock_llm = Mock()
|
||||
with patch.object(LLM, "supports_function_calling") as supports_function_calling:
|
||||
supports_function_calling.return_value = False
|
||||
with patch("crewai.utilities.converter.PydanticSchemaParser") as mock_parser:
|
||||
mock_parser.return_value.get_schema.return_value = "Sample schema"
|
||||
instructions = get_conversion_instructions(SimpleModel, mock_llm)
|
||||
assert "Sample schema" in instructions
|
||||
llm = LLM(model="ollama/llama3.1", base_url="http://localhost:11434")
|
||||
with patch.object(LLM, "supports_function_calling", return_value=False):
|
||||
instructions = get_conversion_instructions(SimpleModel, llm)
|
||||
assert '"name": str' in instructions
|
||||
assert '"age": int' in instructions
|
||||
|
||||
|
||||
# Tests for is_gpt
|
||||
@@ -232,10 +245,6 @@ def test_supports_function_calling_false():
|
||||
assert llm.supports_function_calling() is False
|
||||
|
||||
|
||||
class CustomConverter(Converter):
|
||||
pass
|
||||
|
||||
|
||||
def test_create_converter_with_mock_agent():
|
||||
mock_agent = MagicMock()
|
||||
mock_agent.get_output_converter.return_value = MagicMock(spec=Converter)
|
||||
@@ -255,7 +264,7 @@ def test_create_converter_with_mock_agent():
|
||||
def test_create_converter_with_custom_converter():
|
||||
converter = create_converter(
|
||||
converter_cls=CustomConverter,
|
||||
llm=Mock(),
|
||||
llm=LLM(model="gpt-4o-mini"),
|
||||
text="Sample",
|
||||
model=SimpleModel,
|
||||
instructions="Convert",
|
||||
@@ -313,3 +322,269 @@ def test_generate_model_description_dict_field():
|
||||
description = generate_model_description(ModelWithDictField)
|
||||
expected_description = '{\n "attributes": Dict[str, int]\n}'
|
||||
assert description == expected_description
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_convert_with_instructions():
|
||||
llm = LLM(model="gpt-4o-mini")
|
||||
sample_text = "Name: Alice, Age: 30"
|
||||
|
||||
instructions = get_conversion_instructions(SimpleModel, llm)
|
||||
converter = Converter(
|
||||
llm=llm,
|
||||
text=sample_text,
|
||||
model=SimpleModel,
|
||||
instructions=instructions,
|
||||
)
|
||||
|
||||
# Act
|
||||
output = converter.to_pydantic()
|
||||
|
||||
# Assert
|
||||
assert isinstance(output, SimpleModel)
|
||||
assert output.name == "Alice"
|
||||
assert output.age == 30
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_converter_with_llama3_2_model():
|
||||
llm = LLM(model="ollama/llama3.2:3b", base_url="http://localhost:11434")
|
||||
|
||||
sample_text = "Name: Alice Llama, Age: 30"
|
||||
|
||||
instructions = get_conversion_instructions(SimpleModel, llm)
|
||||
converter = Converter(
|
||||
llm=llm,
|
||||
text=sample_text,
|
||||
model=SimpleModel,
|
||||
instructions=instructions,
|
||||
)
|
||||
|
||||
output = converter.to_pydantic()
|
||||
|
||||
assert isinstance(output, SimpleModel)
|
||||
assert output.name == "Alice Llama"
|
||||
assert output.age == 30
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_converter_with_llama3_1_model():
|
||||
llm = LLM(model="ollama/llama3.1", base_url="http://localhost:11434")
|
||||
sample_text = "Name: Alice Llama, Age: 30"
|
||||
|
||||
instructions = get_conversion_instructions(SimpleModel, llm)
|
||||
converter = Converter(
|
||||
llm=llm,
|
||||
text=sample_text,
|
||||
model=SimpleModel,
|
||||
instructions=instructions,
|
||||
)
|
||||
|
||||
output = converter.to_pydantic()
|
||||
|
||||
assert isinstance(output, SimpleModel)
|
||||
assert output.name == "Alice Llama"
|
||||
assert output.age == 30
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_converter_with_nested_model():
|
||||
llm = LLM(model="gpt-4o-mini")
|
||||
sample_text = "Name: John Doe\nAge: 30\nAddress: 123 Main St, Anytown, 12345"
|
||||
|
||||
instructions = get_conversion_instructions(Person, llm)
|
||||
converter = Converter(
|
||||
llm=llm,
|
||||
text=sample_text,
|
||||
model=Person,
|
||||
instructions=instructions,
|
||||
)
|
||||
|
||||
output = converter.to_pydantic()
|
||||
|
||||
assert isinstance(output, Person)
|
||||
assert output.name == "John Doe"
|
||||
assert output.age == 30
|
||||
assert isinstance(output.address, Address)
|
||||
assert output.address.street == "123 Main St"
|
||||
assert output.address.city == "Anytown"
|
||||
assert output.address.zip_code == "12345"
|
||||
|
||||
|
||||
# Tests for error handling
|
||||
def test_converter_error_handling():
|
||||
llm = Mock(spec=LLM)
|
||||
llm.supports_function_calling.return_value = False
|
||||
llm.call.return_value = "Invalid JSON"
|
||||
sample_text = "Name: Alice, Age: 30"
|
||||
|
||||
instructions = get_conversion_instructions(SimpleModel, llm)
|
||||
converter = Converter(
|
||||
llm=llm,
|
||||
text=sample_text,
|
||||
model=SimpleModel,
|
||||
instructions=instructions,
|
||||
)
|
||||
|
||||
with pytest.raises(ConverterError) as exc_info:
|
||||
output = converter.to_pydantic()
|
||||
|
||||
assert "Failed to convert text into a Pydantic model" in str(exc_info.value)
|
||||
|
||||
|
||||
# Tests for retry logic
|
||||
def test_converter_retry_logic():
|
||||
llm = Mock(spec=LLM)
|
||||
llm.supports_function_calling.return_value = False
|
||||
llm.call.side_effect = [
|
||||
"Invalid JSON",
|
||||
"Still invalid",
|
||||
'{"name": "Retry Alice", "age": 30}',
|
||||
]
|
||||
sample_text = "Name: Retry Alice, Age: 30"
|
||||
|
||||
instructions = get_conversion_instructions(SimpleModel, llm)
|
||||
converter = Converter(
|
||||
llm=llm,
|
||||
text=sample_text,
|
||||
model=SimpleModel,
|
||||
instructions=instructions,
|
||||
max_attempts=3,
|
||||
)
|
||||
|
||||
output = converter.to_pydantic()
|
||||
|
||||
assert isinstance(output, SimpleModel)
|
||||
assert output.name == "Retry Alice"
|
||||
assert output.age == 30
|
||||
assert llm.call.call_count == 3
|
||||
|
||||
|
||||
# Tests for optional fields
|
||||
def test_converter_with_optional_fields():
|
||||
class OptionalModel(BaseModel):
|
||||
name: str
|
||||
age: Optional[int]
|
||||
|
||||
llm = Mock(spec=LLM)
|
||||
llm.supports_function_calling.return_value = False
|
||||
# Simulate the LLM's response with 'age' explicitly set to null
|
||||
llm.call.return_value = '{"name": "Bob", "age": null}'
|
||||
sample_text = "Name: Bob, age: None"
|
||||
|
||||
instructions = get_conversion_instructions(OptionalModel, llm)
|
||||
converter = Converter(
|
||||
llm=llm,
|
||||
text=sample_text,
|
||||
model=OptionalModel,
|
||||
instructions=instructions,
|
||||
)
|
||||
|
||||
output = converter.to_pydantic()
|
||||
|
||||
assert isinstance(output, OptionalModel)
|
||||
assert output.name == "Bob"
|
||||
assert output.age is None
|
||||
|
||||
|
||||
# Tests for list fields
|
||||
def test_converter_with_list_field():
|
||||
class ListModel(BaseModel):
|
||||
items: List[int]
|
||||
|
||||
llm = Mock(spec=LLM)
|
||||
llm.supports_function_calling.return_value = False
|
||||
llm.call.return_value = '{"items": [1, 2, 3]}'
|
||||
sample_text = "Items: 1, 2, 3"
|
||||
|
||||
instructions = get_conversion_instructions(ListModel, llm)
|
||||
converter = Converter(
|
||||
llm=llm,
|
||||
text=sample_text,
|
||||
model=ListModel,
|
||||
instructions=instructions,
|
||||
)
|
||||
|
||||
output = converter.to_pydantic()
|
||||
|
||||
assert isinstance(output, ListModel)
|
||||
assert output.items == [1, 2, 3]
|
||||
|
||||
|
||||
# Tests for enums
|
||||
from enum import Enum
|
||||
|
||||
|
||||
def test_converter_with_enum():
|
||||
class Color(Enum):
|
||||
RED = "red"
|
||||
GREEN = "green"
|
||||
BLUE = "blue"
|
||||
|
||||
class EnumModel(BaseModel):
|
||||
name: str
|
||||
color: Color
|
||||
|
||||
llm = Mock(spec=LLM)
|
||||
llm.supports_function_calling.return_value = False
|
||||
llm.call.return_value = '{"name": "Alice", "color": "red"}'
|
||||
sample_text = "Name: Alice, Color: Red"
|
||||
|
||||
instructions = get_conversion_instructions(EnumModel, llm)
|
||||
converter = Converter(
|
||||
llm=llm,
|
||||
text=sample_text,
|
||||
model=EnumModel,
|
||||
instructions=instructions,
|
||||
)
|
||||
|
||||
output = converter.to_pydantic()
|
||||
|
||||
assert isinstance(output, EnumModel)
|
||||
assert output.name == "Alice"
|
||||
assert output.color == Color.RED
|
||||
|
||||
|
||||
# Tests for ambiguous input
|
||||
def test_converter_with_ambiguous_input():
|
||||
llm = Mock(spec=LLM)
|
||||
llm.supports_function_calling.return_value = False
|
||||
llm.call.return_value = '{"name": "Charlie", "age": "Not an age"}'
|
||||
sample_text = "Charlie is thirty years old"
|
||||
|
||||
instructions = get_conversion_instructions(SimpleModel, llm)
|
||||
converter = Converter(
|
||||
llm=llm,
|
||||
text=sample_text,
|
||||
model=SimpleModel,
|
||||
instructions=instructions,
|
||||
)
|
||||
|
||||
with pytest.raises(ConverterError) as exc_info:
|
||||
output = converter.to_pydantic()
|
||||
|
||||
assert "validation error" in str(exc_info.value).lower()
|
||||
|
||||
|
||||
# Tests for function calling support
|
||||
def test_converter_with_function_calling():
|
||||
llm = Mock(spec=LLM)
|
||||
llm.supports_function_calling.return_value = True
|
||||
|
||||
instructor = Mock()
|
||||
instructor.to_pydantic.return_value = SimpleModel(name="Eve", age=35)
|
||||
|
||||
converter = Converter(
|
||||
llm=llm,
|
||||
text="Name: Eve, Age: 35",
|
||||
model=SimpleModel,
|
||||
instructions="Convert this text.",
|
||||
)
|
||||
converter._create_instructor = Mock(return_value=instructor)
|
||||
|
||||
output = converter.to_pydantic()
|
||||
|
||||
assert isinstance(output, SimpleModel)
|
||||
assert output.name == "Eve"
|
||||
assert output.age == 35
|
||||
instructor.to_pydantic.assert_called_once()
|
||||
|
||||
94
tests/utilities/test_pydantic_schema_parser.py
Normal file
94
tests/utilities/test_pydantic_schema_parser.py
Normal file
@@ -0,0 +1,94 @@
|
||||
from typing import Any, Dict, List, Optional, Set, Tuple, Union
|
||||
|
||||
import pytest
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
|
||||
|
||||
|
||||
def test_simple_model():
|
||||
class SimpleModel(BaseModel):
|
||||
field1: int
|
||||
field2: str
|
||||
|
||||
parser = PydanticSchemaParser(model=SimpleModel)
|
||||
schema = parser.get_schema()
|
||||
|
||||
expected_schema = """{
|
||||
field1: int,
|
||||
field2: str
|
||||
}"""
|
||||
assert schema.strip() == expected_schema.strip()
|
||||
|
||||
|
||||
def test_nested_model():
|
||||
class NestedModel(BaseModel):
|
||||
nested_field: int
|
||||
|
||||
class ParentModel(BaseModel):
|
||||
parent_field: str
|
||||
nested: NestedModel
|
||||
|
||||
parser = PydanticSchemaParser(model=ParentModel)
|
||||
schema = parser.get_schema()
|
||||
|
||||
expected_schema = """{
|
||||
parent_field: str,
|
||||
nested: NestedModel
|
||||
{
|
||||
nested_field: int
|
||||
}
|
||||
}"""
|
||||
assert schema.strip() == expected_schema.strip()
|
||||
|
||||
|
||||
def test_model_with_list():
|
||||
class ListModel(BaseModel):
|
||||
list_field: List[int]
|
||||
|
||||
parser = PydanticSchemaParser(model=ListModel)
|
||||
schema = parser.get_schema()
|
||||
|
||||
expected_schema = """{
|
||||
list_field: List[int]
|
||||
}"""
|
||||
assert schema.strip() == expected_schema.strip()
|
||||
|
||||
|
||||
def test_model_with_optional_field():
|
||||
class OptionalModel(BaseModel):
|
||||
optional_field: Optional[str]
|
||||
|
||||
parser = PydanticSchemaParser(model=OptionalModel)
|
||||
schema = parser.get_schema()
|
||||
|
||||
expected_schema = """{
|
||||
optional_field: Optional[str]
|
||||
}"""
|
||||
assert schema.strip() == expected_schema.strip()
|
||||
|
||||
|
||||
def test_model_with_union():
|
||||
class UnionModel(BaseModel):
|
||||
union_field: Union[int, str]
|
||||
|
||||
parser = PydanticSchemaParser(model=UnionModel)
|
||||
schema = parser.get_schema()
|
||||
|
||||
expected_schema = """{
|
||||
union_field: Union[int, str]
|
||||
}"""
|
||||
assert schema.strip() == expected_schema.strip()
|
||||
|
||||
|
||||
def test_model_with_dict():
|
||||
class DictModel(BaseModel):
|
||||
dict_field: Dict[str, int]
|
||||
|
||||
parser = PydanticSchemaParser(model=DictModel)
|
||||
schema = parser.get_schema()
|
||||
|
||||
expected_schema = """{
|
||||
dict_field: Dict[str, int]
|
||||
}"""
|
||||
assert schema.strip() == expected_schema.strip()
|
||||
Reference in New Issue
Block a user