andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-07 15:18:29 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity
Files
3731053c83c6370993c2294830c26f8a2c1e9634
crewAI/tests/cassettes/test_agent_function_calling_llm.yaml
Brandon Hancock (bhancock_ai) 2131b94ddb Fixed core invoke loop logic and relevant tests (#1865) 
* Fixed core invoke loop logic and relevant tests

* Fix failing tests

* Clean up final print statements

* Additional clean up for PR review
2025-01-09 12:13:02 -05:00

1399 lines
61 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\nTool
Arguments: {}\nTool Description: Useful for when you need to learn about AI
to write an paragraph about it.\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"}, {"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": ["\nObservation:"], "stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1338'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
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-AnT5xg0d2oSpdM98uCn4hkLf3nxVm\",\n \"object\":
\"chat.completion\",\n \"created\": 1736353277,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to gather information
about AI to write an amazing paragraph about it.\\nAction: learn_about_AI\\nAction
Input: {}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
258,\n \"completion_tokens\": 27,\n \"total_tokens\": 285,\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 \"system_fingerprint\":
\"fp_d28bcae782\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8fed85104db7bf78-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 08 Jan 2025 16:21:18 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=utmElwxS9XjsHpYVn5xaGh15uJHFYxzRIGu07xAb6JE-1736353278-1.0.1.1-B8jv6sT4PoFVkmtqk5s29LAJQ8IQWIXmggCq13BPhQFqBtk8M29ZEVDt0BMKFdyGGW9j5GOmQAM2f8UVqrI8sQ;
path=/; expires=Wed, 08-Jan-25 16:51:18 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=0FcCAalOhwLMljvE807Ji4XmVbjXjgRhfa_EYkd_gNo-1736353278255-0.0.1.1-604800000;
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:
- '694'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999689'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_120e0f608bf4f06d238ed755b9cd7bb9
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Only tools available:\n###\nTool
Name: learn_about_AI\nTool Arguments: {}\nTool Description: Useful for when
you need to learn about AI to write an paragraph about it.\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 \nThought: I need
to gather information about AI to write an amazing paragraph about it.\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 (always a dictionary, 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:
- '1446'
content-type:
- application/json
cookie:
- __cf_bm=utmElwxS9XjsHpYVn5xaGh15uJHFYxzRIGu07xAb6JE-1736353278-1.0.1.1-B8jv6sT4PoFVkmtqk5s29LAJQ8IQWIXmggCq13BPhQFqBtk8M29ZEVDt0BMKFdyGGW9j5GOmQAM2f8UVqrI8sQ;
_cfuvid=0FcCAalOhwLMljvE807Ji4XmVbjXjgRhfa_EYkd_gNo-1736353278255-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
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-AnT5yyloXQ2UcC56oaRo8uxsP4pRf\",\n \"object\":
\"chat.completion\",\n \"created\": 1736353278,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_zoRBWYhlaZPlJNwSabr07o6B\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"InstructorToolCalling\",\n
\ \"arguments\": \"{\\\"tool_name\\\":\\\"learn_about_AI\\\",\\\"arguments\\\":{}}\"\n
\ }\n }\n ],\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 260,\n \"completion_tokens\": 12,\n
\ \"total_tokens\": 272,\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 \"system_fingerprint\":
\"fp_d28bcae782\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8fed8515ad1ebf78-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 08 Jan 2025 16:21:19 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:
- '567'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999809'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_de894e2856e173f2f6c89de79e8200a8
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Only tools available:\n###\nTool
Name: learn_about_AI\nTool Arguments: {}\nTool Description: Useful for when
you need to learn about AI to write an paragraph about it.\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 \nThought: I need
to gather information about AI to write an amazing paragraph about it.\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 (always a dictionary, 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:
- '1446'
content-type:
- application/json
cookie:
- __cf_bm=utmElwxS9XjsHpYVn5xaGh15uJHFYxzRIGu07xAb6JE-1736353278-1.0.1.1-B8jv6sT4PoFVkmtqk5s29LAJQ8IQWIXmggCq13BPhQFqBtk8M29ZEVDt0BMKFdyGGW9j5GOmQAM2f8UVqrI8sQ;
_cfuvid=0FcCAalOhwLMljvE807Ji4XmVbjXjgRhfa_EYkd_gNo-1736353278255-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
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-AnT5zFbAWZwyOX6paZVBynwtWoWf6\",\n \"object\":
\"chat.completion\",\n \"created\": 1736353279,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_cVNL3a0GemLIG52sJCgri6Qk\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"InstructorToolCalling\",\n
\ \"arguments\": \"{\\\"tool_name\\\":\\\"learn_about_AI\\\",\\\"arguments\\\":{}}\"\n
\ }\n }\n ],\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 260,\n \"completion_tokens\": 13,\n
\ \"total_tokens\": 273,\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 \"system_fingerprint\":
\"fp_d28bcae782\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8fed851a1b18bf78-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 08 Jan 2025 16:21:19 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:
- '663'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999810'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_904150df078104dc6ceb6f08beab997a
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Only tools available:\n###\nTool
Name: learn_about_AI\nTool Arguments: {}\nTool Description: Useful for when
you need to learn about AI to write an paragraph about it.\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 \nThought: I need
to gather information about AI to write an amazing paragraph about it.\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 (always a dictionary, 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:
- '1446'
content-type:
- application/json
cookie:
- __cf_bm=utmElwxS9XjsHpYVn5xaGh15uJHFYxzRIGu07xAb6JE-1736353278-1.0.1.1-B8jv6sT4PoFVkmtqk5s29LAJQ8IQWIXmggCq13BPhQFqBtk8M29ZEVDt0BMKFdyGGW9j5GOmQAM2f8UVqrI8sQ;
_cfuvid=0FcCAalOhwLMljvE807Ji4XmVbjXjgRhfa_EYkd_gNo-1736353278255-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
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-AnT5zfhawVHK8B0cbr3OxiJFxLtzo\",\n \"object\":
\"chat.completion\",\n \"created\": 1736353279,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_VF7TyvP79HE2KgwkeUCBCyLy\",\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\": 260,\n \"completion_tokens\": 13,\n
\ \"total_tokens\": 273,\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 \"system_fingerprint\":
\"fp_d28bcae782\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8fed851f0a41bf78-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 08 Jan 2025 16:21:20 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:
- '516'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999810'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_c7bc45f498821f58c158480ae5545d58
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |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=
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1424'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Wed, 08 Jan 2025 16:21:21 GMT
status:
code: 200
message: OK
- 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\nTool
Arguments: {}\nTool Description: Useful for when you need to learn about AI
to write an paragraph about it.\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"}, {"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": "Thought: I need to gather information about AI to write
an amazing paragraph about it.\nAction: learn_about_AI\nAction Input: {}\nObservation:
I encountered an error: ''InstructorToolCalling'' object is not subscriptable\nMoving
on then. I MUST either use a tool (use one at time) OR give my best final answer
not both at the same time. To Use the following format:\n\nThought: you should
always think about what to do\nAction: the action to take, should be one of
[learn_about_AI]\nAction Input: the input to the action, dictionary enclosed
in curly braces\nObservation: the result of the action\n... (this Thought/Action/Action
Input/Result can repeat N times)\nThought: I now can give a great answer\nFinal
Answer: Your final answer must be the great and the most complete as possible,
it must be outcome described"}], "model": "gpt-4o", "stop": ["\nObservation:"],
"stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2191'
content-type:
- application/json
cookie:
- __cf_bm=utmElwxS9XjsHpYVn5xaGh15uJHFYxzRIGu07xAb6JE-1736353278-1.0.1.1-B8jv6sT4PoFVkmtqk5s29LAJQ8IQWIXmggCq13BPhQFqBtk8M29ZEVDt0BMKFdyGGW9j5GOmQAM2f8UVqrI8sQ;
_cfuvid=0FcCAalOhwLMljvE807Ji4XmVbjXjgRhfa_EYkd_gNo-1736353278255-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
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-AnT60p3OY22u97AGextIFTa8K8HsB\",\n \"object\":
\"chat.completion\",\n \"created\": 1736353280,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to attempt using the
tool again to gather accurate information about AI to write an exceptional 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\": 441,\n \"completion_tokens\": 32,\n
\ \"total_tokens\": 473,\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 \"system_fingerprint\":
\"fp_d28bcae782\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8fed8522ff56bf78-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 08 Jan 2025 16:21:21 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:
- '1084'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999489'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_ed4fc81b204c0aae53a00857eb56c5a9
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Only tools available:\n###\nTool
Name: learn_about_AI\nTool Arguments: {}\nTool Description: Useful for when
you need to learn about AI to write an paragraph about it.\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 \nThought: I need
to attempt using the tool again to gather accurate information about AI to write
an exceptional 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 (always a dictionary, 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:
- '1484'
content-type:
- application/json
cookie:
- __cf_bm=utmElwxS9XjsHpYVn5xaGh15uJHFYxzRIGu07xAb6JE-1736353278-1.0.1.1-B8jv6sT4PoFVkmtqk5s29LAJQ8IQWIXmggCq13BPhQFqBtk8M29ZEVDt0BMKFdyGGW9j5GOmQAM2f8UVqrI8sQ;
_cfuvid=0FcCAalOhwLMljvE807Ji4XmVbjXjgRhfa_EYkd_gNo-1736353278255-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
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-AnT61zkErrL6IkmAgHpgTGbrKhQEp\",\n \"object\":
\"chat.completion\",\n \"created\": 1736353281,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_0322HkWSEfvLot1ProE7Eu7z\",\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\": 265,\n \"completion_tokens\": 13,\n
\ \"total_tokens\": 278,\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 \"system_fingerprint\":
\"fp_d28bcae782\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8fed852a6941bf78-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 08 Jan 2025 16:21:22 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:
- '528'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999801'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_6e0513d59b026c6faf94262e6cf39464
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Only tools available:\n###\nTool
Name: learn_about_AI\nTool Arguments: {}\nTool Description: Useful for when
you need to learn about AI to write an paragraph about it.\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 \nThought: I need
to attempt using the tool again to gather accurate information about AI to write
an exceptional 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 (always a dictionary, 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:
- '1484'
content-type:
- application/json
cookie:
- __cf_bm=utmElwxS9XjsHpYVn5xaGh15uJHFYxzRIGu07xAb6JE-1736353278-1.0.1.1-B8jv6sT4PoFVkmtqk5s29LAJQ8IQWIXmggCq13BPhQFqBtk8M29ZEVDt0BMKFdyGGW9j5GOmQAM2f8UVqrI8sQ;
_cfuvid=0FcCAalOhwLMljvE807Ji4XmVbjXjgRhfa_EYkd_gNo-1736353278255-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
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-AnT62qG840k70wb8XXN6ImpxcBS8x\",\n \"object\":
\"chat.completion\",\n \"created\": 1736353282,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_hSsjdxtbOhHoiJm2BO7sDecX\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"InstructorToolCalling\",\n
\ \"arguments\": \"{\\\"tool_name\\\":\\\"learn_about_AI\\\",\\\"arguments\\\":{}}\"\n
\ }\n }\n ],\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 265,\n \"completion_tokens\": 13,\n
\ \"total_tokens\": 278,\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 \"system_fingerprint\":
\"fp_d28bcae782\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8fed852efeeebf78-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 08 Jan 2025 16:21:23 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:
- '546'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999801'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_7d811037f9b7c92d19b65c138b5e9faf
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Only tools available:\n###\nTool
Name: learn_about_AI\nTool Arguments: {}\nTool Description: Useful for when
you need to learn about AI to write an paragraph about it.\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 \nThought: I need
to attempt using the tool again to gather accurate information about AI to write
an exceptional 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 (always a dictionary, 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:
- '1484'
content-type:
- application/json
cookie:
- __cf_bm=utmElwxS9XjsHpYVn5xaGh15uJHFYxzRIGu07xAb6JE-1736353278-1.0.1.1-B8jv6sT4PoFVkmtqk5s29LAJQ8IQWIXmggCq13BPhQFqBtk8M29ZEVDt0BMKFdyGGW9j5GOmQAM2f8UVqrI8sQ;
_cfuvid=0FcCAalOhwLMljvE807Ji4XmVbjXjgRhfa_EYkd_gNo-1736353278255-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
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-AnT63LzJID9lUH7bdWCzFr6SvTjeT\",\n \"object\":
\"chat.completion\",\n \"created\": 1736353283,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_6DDvnFuU35Y0CcFlKYmue1ZY\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"InstructorToolCalling\",\n
\ \"arguments\": \"{\\\"tool_name\\\":\\\"learn_about_AI\\\",\\\"arguments\\\":{}}\"\n
\ }\n }\n ],\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 265,\n \"completion_tokens\": 13,\n
\ \"total_tokens\": 278,\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 \"system_fingerprint\":
\"fp_d28bcae782\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8fed85332ca2bf78-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 08 Jan 2025 16:21:23 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:
- '577'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999801'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_69d812e7e64ce52f86bb8cc1ad5332b9
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
CrgBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSjwEKEgoQY3Jld2FpLnRl
bGVtZXRyeRJ5ChDjSABIUI5uC365BJqSK54sEghB1g/8AKfnHioQVG9vbCBVc2FnZSBFcnJvcjAB
OcCmHqUcxBgYQRgDKaUcxBgYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuOTUuMEoPCgNsbG0SCAoG
Z3B0LTRvegIYAYUBAAEAAA==
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '187'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Wed, 08 Jan 2025 16:21:26 GMT
status:
code: 200
message: OK
- 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\nTool
Arguments: {}\nTool Description: Useful for when you need to learn about AI
to write an paragraph about it.\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"}, {"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": "Thought: I need to gather information about AI to write
an amazing paragraph about it.\nAction: learn_about_AI\nAction Input: {}\nObservation:
I encountered an error: ''InstructorToolCalling'' object is not subscriptable\nMoving
on then. I MUST either use a tool (use one at time) OR give my best final answer
not both at the same time. To Use the following format:\n\nThought: you should
always think about what to do\nAction: the action to take, should be one of
[learn_about_AI]\nAction Input: the input to the action, dictionary enclosed
in curly braces\nObservation: the result of the action\n... (this Thought/Action/Action
Input/Result can repeat N times)\nThought: I now can give a great answer\nFinal
Answer: Your final answer must be the great and the most complete as possible,
it must be outcome described"}, {"role": "assistant", "content": "Thought: I
need to attempt using the tool again to gather accurate information about AI
to write an exceptional paragraph.\n\nAction: learn_about_AI\nAction Input:
{}\nObservation: I encountered an error: ''InstructorToolCalling'' object is
not subscriptable\nMoving on then. I MUST either use a tool (use one at time)
OR give my best final answer not both at the same time. To Use the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, should be one of [learn_about_AI]\nAction Input: the input to the action,
dictionary enclosed in curly braces\nObservation: the result of the action\n...
(this Thought/Action/Action Input/Result can repeat N times)\nThought: I now
can give a great answer\nFinal Answer: Your final answer must be the great and
the most complete as possible, it must be outcome described"}, {"role": "assistant",
"content": "Thought: I need to attempt using the tool again to gather accurate
information about AI to write an exceptional paragraph.\n\nAction: learn_about_AI\nAction
Input: {}\nObservation: I encountered an error: ''InstructorToolCalling'' object
is not subscriptable\nMoving on then. I MUST either use a tool (use one at time)
OR give my best final answer not both at the same time. To Use the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, should be one of [learn_about_AI]\nAction Input: the input to the action,
dictionary enclosed in curly braces\nObservation: the result of the action\n...
(this Thought/Action/Action Input/Result can repeat N times)\nThought: I now
can give a great answer\nFinal Answer: Your final answer must be the great and
the most complete as possible, it must be outcome described\n\n\nNow it''s time
you MUST give your absolute best final answer. You''ll ignore all previous instructions,
stop using any tools, and just return your absolute BEST Final answer."}], "model":
"gpt-4o", "stop": ["\nObservation:"], "stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '4151'
content-type:
- application/json
cookie:
- __cf_bm=utmElwxS9XjsHpYVn5xaGh15uJHFYxzRIGu07xAb6JE-1736353278-1.0.1.1-B8jv6sT4PoFVkmtqk5s29LAJQ8IQWIXmggCq13BPhQFqBtk8M29ZEVDt0BMKFdyGGW9j5GOmQAM2f8UVqrI8sQ;
_cfuvid=0FcCAalOhwLMljvE807Ji4XmVbjXjgRhfa_EYkd_gNo-1736353278255-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
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-AnT63puviaZGTpoYqojXbfoXuVAyB\",\n \"object\":
\"chat.completion\",\n \"created\": 1736353283,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"AI, or artificial intelligence, is revolutionizing
the way we interact with technology and the world around us. It encompasses
a wide range of technologies and methodologies that allow machines to mimic
human intelligence. This includes learning from data, understanding natural
language, recognizing patterns, and solving complex problems. The impact of
AI is evident across various sectors such as healthcare, where it aids in diagnosing
diseases with high precision; in automotive, where it's pivotal in the development
of autonomous vehicles; and in everyday consumer products like smartphones and
home assistants, which intuitively cater to our needs. As AI continues to advance,
it promises to bring about substantial societal changes, enhancing efficiency,
fostering innovation, and opening new possibilities that were once considered
the realm of science fiction.\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
850,\n \"completion_tokens\": 146,\n \"total_tokens\": 996,\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 \"system_fingerprint\":
\"fp_d28bcae782\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8fed85374a75bf78-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 08 Jan 2025 16:21:32 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:
- '8768'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999022'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_d122f197f29303e039bae1e5dac2035b
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\nTool
Arguments: {}\nTool Description: Useful for when you need to learn about AI
to write an paragraph about it.\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"}, {"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": "Thought: I need to gather information about AI to write
an amazing paragraph about it.\nAction: learn_about_AI\nAction Input: {}\nObservation:
I encountered an error: ''InstructorToolCalling'' object is not subscriptable\nMoving
on then. I MUST either use a tool (use one at time) OR give my best final answer
not both at the same time. To Use the following format:\n\nThought: you should
always think about what to do\nAction: the action to take, should be one of
[learn_about_AI]\nAction Input: the input to the action, dictionary enclosed
in curly braces\nObservation: the result of the action\n... (this Thought/Action/Action
Input/Result can repeat N times)\nThought: I now can give a great answer\nFinal
Answer: Your final answer must be the great and the most complete as possible,
it must be outcome described"}, {"role": "assistant", "content": "Thought: I
need to attempt using the tool again to gather accurate information about AI
to write an exceptional paragraph.\n\nAction: learn_about_AI\nAction Input:
{}\nObservation: I encountered an error: ''InstructorToolCalling'' object is
not subscriptable\nMoving on then. I MUST either use a tool (use one at time)
OR give my best final answer not both at the same time. To Use the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, should be one of [learn_about_AI]\nAction Input: the input to the action,
dictionary enclosed in curly braces\nObservation: the result of the action\n...
(this Thought/Action/Action Input/Result can repeat N times)\nThought: I now
can give a great answer\nFinal Answer: Your final answer must be the great and
the most complete as possible, it must be outcome described"}, {"role": "assistant",
"content": "Thought: I need to attempt using the tool again to gather accurate
information about AI to write an exceptional paragraph.\n\nAction: learn_about_AI\nAction
Input: {}\nObservation: I encountered an error: ''InstructorToolCalling'' object
is not subscriptable\nMoving on then. I MUST either use a tool (use one at time)
OR give my best final answer not both at the same time. To Use the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, should be one of [learn_about_AI]\nAction Input: the input to the action,
dictionary enclosed in curly braces\nObservation: the result of the action\n...
(this Thought/Action/Action Input/Result can repeat N times)\nThought: I now
can give a great answer\nFinal Answer: Your final answer must be the great and
the most complete as possible, it must be outcome described\n\n\nNow it''s time
you MUST give your absolute best final answer. You''ll ignore all previous instructions,
stop using any tools, and just return your absolute BEST Final answer."}, {"role":
"user", "content": "I did it wrong. Invalid Format: I missed the ''Action:''
after ''Thought:''. I will do right next, and don''t use a tool I have already
used.\n\nIf you don''t need to use any more tools, you must give your best complete
final answer, make sure it satisfies the expected criteria, use the EXACT format
below:\n\nThought: I now can give a great answer\nFinal Answer: my best complete
final answer to the task.\n\n"}, {"role": "assistant", "content": "I did it
wrong. Invalid Format: I missed the ''Action:'' after ''Thought:''. I will do
right next, and don''t use a tool I have already used.\n\nIf you don''t need
to use any more tools, you must give your best complete final answer, make sure
it satisfies the expected criteria, use the EXACT format below:\n\nThought:
I now can give a great answer\nFinal Answer: my best complete final answer to
the task.\n\n\nNow it''s time you MUST give your absolute best final answer.
You''ll ignore all previous instructions, stop using any tools, and just return
your absolute BEST Final answer."}], "model": "gpt-4o", "stop": ["\nObservation:"],
"stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '5206'
content-type:
- application/json
cookie:
- __cf_bm=utmElwxS9XjsHpYVn5xaGh15uJHFYxzRIGu07xAb6JE-1736353278-1.0.1.1-B8jv6sT4PoFVkmtqk5s29LAJQ8IQWIXmggCq13BPhQFqBtk8M29ZEVDt0BMKFdyGGW9j5GOmQAM2f8UVqrI8sQ;
_cfuvid=0FcCAalOhwLMljvE807Ji4XmVbjXjgRhfa_EYkd_gNo-1736353278255-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
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-AnT6ChI9bdKBSgBW4M1oA1wIZs0i4\",\n \"object\":
\"chat.completion\",\n \"created\": 1736353292,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: Artificial Intelligence (AI) is revolutionizing the way we interact
with technology, enabling machines to perform tasks that typically require human
intelligence. From natural language processing and computer vision to decision-making
and problem-solving, AI is increasingly becoming an integral part of various
industries. Its ability to analyze vast amounts of data quickly and accurately
allows businesses to automate processes, enhance customer experiences, and make
informed decisions. As AI continues to advance, it holds the potential to drive
innovation, improve efficiency, and address complex global challenges, ultimately
transforming society in unprecedented ways. However, this rapid development
also raises ethical considerations, emphasizing the need for responsible AI
that aligns with human values.\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
1070,\n \"completion_tokens\": 142,\n \"total_tokens\": 1212,\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 \"system_fingerprint\":
\"fp_d28bcae782\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8fed856ecdb0bf78-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 08 Jan 2025 16:21:36 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:
- '3685'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29998779'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_071cc236ce92053484d2bf04d80b83eb
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink