andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-11 09:08:31 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity
Files
f216b0a78c5138ed4e0b4fe6715b5d7ac888d872
crewAI/tests/cassettes/test_agent_function_calling_llm.yaml
João Moura f216b0a78c fixing parser, tools and executor
2024-09-15 18:41:59 -03:00

370 lines
16 KiB
YAML
Raw Blame History

interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: learn_about_AI(*args:
Any, **kwargs: Any) -> Any\nTool Description: learn_about_AI() - Useful for
when you need to learn about AI to write an paragraph about it. \nTool Arguments:
{}\n\nUse the following format:\n\nThought: you should always think about what
to do\nAction: the action to take, only one name of [learn_about_AI], just the
name, exactly as it''s written.\nAction Input: the input to the action, just
a simple python dictionary, enclosed in curly braces, using \" to wrap keys
and values.\nObservation: the result of the action\n\nOnce all necessary information
is gathered:\n\nThought: I now know the final answer\nFinal Answer: the final
answer to the original input question\n"}, {"role": "user", "content": "\nCurrent
Task: Write and then review an small paragraph on AI until it''s AMAZING\n\nThis
is the expect criteria for your final answer: The final paragraph.\nyou MUST
return the actual complete content as the final answer, not a summary.\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nResult"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1371'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A7pYOSyCOlKTkdDHBdEGwBc8Q9Rcg\",\n \"object\":
\"chat.completion\",\n \"created\": 1726429832,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I need to gather information about AI
to write an excellent paragraph. \\n\\nAction: learn_about_AI\\nAction Input:
{}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 277,\n \"completion_tokens\":
24,\n \"total_tokens\": 301,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3b2572ba927431-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 15 Sep 2024 19:50:32 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=FibOHMztCGP4kfVoS9BookQQGZtYBbmHXjtxEfZ..TU-1726429832-1.0.1.1-lrRK2EAGi8KuD70I.39t4tx0NkwutIhWn.vwMMIEnaijDRNqGNmezEyeqlLwLMlFGnfpapINdyJdCMhYqEg1Ow;
path=/; expires=Sun, 15-Sep-24 20:20:32 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=l2b2oP3HqGQzHTnAoFlscZueCqkrQ8_AiB_5gvF1K7U-1726429832537-0.0.1.1-604800000;
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:
- '269'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999677'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_09fae8d84a569255697f32b1dec4b4b8
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Only tools available:\n###\nTool
Name: learn_about_ai\nTool Description: learn_about_AI() - Useful for when you
need to learn about AI to write an paragraph about it. \nTool Arguments: {}\n\nReturn
a valid schema for the tool, the tool name must be exactly equal one of the
options, use this text to inform the valid output schema:\n\n### TEXT \nI need
to gather information about AI to write an excellent paragraph. \n\nAction:
learn_about_AI\nAction Input: {}"}, {"role": "system", "content": "The schema
should have the following structure, only two keys:\n- tool_name: str\n- arguments:
dict (with all arguments being passed)\n\nExample:\n{\"tool_name\": \"tool name\",
\"arguments\": {\"arg_name1\": \"value\", \"arg_name2\": 2}}"}], "model": "gpt-4o",
"tool_choice": {"type": "function", "function": {"name": "InstructorToolCalling"}},
"tools": [{"type": "function", "function": {"name": "InstructorToolCalling",
"description": "Correctly extracted `InstructorToolCalling` with all the required
parameters with correct types", "parameters": {"properties": {"tool_name": {"description":
"The name of the tool to be called.", "title": "Tool Name", "type": "string"},
"arguments": {"anyOf": [{"type": "object"}, {"type": "null"}], "description":
"A dictionary of arguments to be passed to the tool.", "title": "Arguments"}},
"required": ["arguments", "tool_name"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1432'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A7pYPq80ttzgRWVxT29zeNTbREDEW\",\n \"object\":
\"chat.completion\",\n \"created\": 1726429833,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_pFDtg2TwvXTD9iMH50NrxA2i\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"InstructorToolCalling\",\n
\ \"arguments\": \"{\\\"tool_name\\\":\\\"learn_about_ai\\\",\\\"arguments\\\":null}\"\n
\ }\n }\n ],\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 259,\n \"completion_tokens\": 12,\n
\ \"total_tokens\": 271,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3b25783ec68ddc-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 15 Sep 2024 19:50:33 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=HYHDoH_NPmJ_d6.NV7B4y7H6jBmyYIdQxtd0qko4NAI-1726429833-1.0.1.1-D3qXDhQcpfXTIkSCCBrsmQ.fJ2Qx4rDkwfEo8QbEPu_MLuA5OPtEMuZ1_SKj7yGzEIbhBRF6X5zLpNhjnAJmjw;
path=/; expires=Sun, 15-Sep-24 20:20:33 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=Vap0Gpj_VfS8LdBJJx_qA58dOZPA5S9majSAGqO4F9U-1726429833360-0.0.1.1-604800000;
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:
- '236'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999813'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_051f2bd4c9c2445bc10cd52c0b4123a6
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: learn_about_AI(*args:
Any, **kwargs: Any) -> Any\nTool Description: learn_about_AI() - Useful for
when you need to learn about AI to write an paragraph about it. \nTool Arguments:
{}\n\nUse the following format:\n\nThought: you should always think about what
to do\nAction: the action to take, only one name of [learn_about_AI], just the
name, exactly as it''s written.\nAction Input: the input to the action, just
a simple python dictionary, enclosed in curly braces, using \" to wrap keys
and values.\nObservation: the result of the action\n\nOnce all necessary information
is gathered:\n\nThought: I now know the final answer\nFinal Answer: the final
answer to the original input question\n"}, {"role": "user", "content": "\nCurrent
Task: Write and then review an small paragraph on AI until it''s AMAZING\n\nThis
is the expect criteria for your final answer: The final paragraph.\nyou MUST
return the actual complete content as the final answer, not a summary.\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}, {"role": "assistant", "content":
"I need to gather information about AI to write an excellent paragraph. \n\nAction:
learn_about_AI\nAction Input: {}\nObservation: AI is a very broad field."}],
"model": "gpt-4o", "stop": ["\nResult"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1564'
content-type:
- application/json
cookie:
- __cf_bm=FibOHMztCGP4kfVoS9BookQQGZtYBbmHXjtxEfZ..TU-1726429832-1.0.1.1-lrRK2EAGi8KuD70I.39t4tx0NkwutIhWn.vwMMIEnaijDRNqGNmezEyeqlLwLMlFGnfpapINdyJdCMhYqEg1Ow;
_cfuvid=l2b2oP3HqGQzHTnAoFlscZueCqkrQ8_AiB_5gvF1K7U-1726429832537-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A7pYPZe2xU0f5FmhdhT3lGQUVGrTH\",\n \"object\":
\"chat.completion\",\n \"created\": 1726429833,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now have the information needed to
write a paragraph. Here it is:\\n\\nArtificial Intelligence (AI) is revolutionizing
the way we live and work by enabling machines to perform tasks that traditionally
required human intelligence. From natural language processing and speech recognition
to autonomous vehicles and personalized recommendations, AI systems are designed
to learn from data, adapt to new inputs, and carry out complex tasks with remarkable
efficiency. AI not only enhances productivity and innovation but also opens
up new frontiers in scientific research, healthcare, and countless other industries.
As we continue to harness the power of AI, it is crucial to ensure ethical considerations
and responsible deployments to maximize its benefits for society while minimizing
potential risks.\\n\\nThought: I believe the paragraph is well-crafted, but
I should review it to ensure it meets the criteria of being amazing.\\n\\nReviewing
the paragraph, it seems informative, cohesive, and highlights the significance
and potential of AI. It also addresses the importance of ethical considerations,
which adds depth.\\n\\nFinal Answer: Artificial Intelligence (AI) is revolutionizing
the way we live and work by enabling machines to perform tasks that traditionally
required human intelligence. From natural language processing and speech recognition
to autonomous vehicles and personalized recommendations, AI systems are designed
to learn from data, adapt to new inputs, and carry out complex tasks with remarkable
efficiency. AI not only enhances productivity and innovation but also opens
up new frontiers in scientific research, healthcare, and countless other industries.
As we continue to harness the power of AI, it is crucial to ensure ethical considerations
and responsible deployments to maximize its benefits for society while minimizing
potential risks.\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
314,\n \"completion_tokens\": 314,\n \"total_tokens\": 628,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3b257b7e607431-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 15 Sep 2024 19:50:36 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:
- '2838'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999637'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_848e03ef6a6129ae5b05bafac981e3ab
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink