andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-08 15:48:29 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity
Files
0ab072a95ed08404260c841f97b706189ae161a7
crewAI/tests/cassettes/test_agent_step_callback.yaml
João Moura 5a3b888f43 Updating all cassetes
2024-09-18 04:17:41 -03:00

1264 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(*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": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1377'
content-type:
- application/json
cookie:
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.46.0
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-A8isdcW9hrigWzaUjwtRFDlm58um2\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642507,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I need to gather detailed information
about AI to write an amazing 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_8dd226ca9c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6db90e5da67a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:55:08 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:
- '301'
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_fec2a48206ece37ddaa568c7a24cc613
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": "user", "content": "I
need to gather detailed information about AI to write an amazing paragraph.\n\nAction:
learn_about_AI\nAction Input: {}\nObservation: AI is a very broad field."}],
"model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1571'
content-type:
- application/json
cookie:
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.46.0
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-A8iseWB5Fq6uuygfyMSDHRuxjXnCD\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642508,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need more specific and comprehensive
information on AI to craft an amazing 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\":
314,\n \"completion_tokens\": 27,\n \"total_tokens\": 341,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_8dd226ca9c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6dbcd851a67a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:55:08 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:
- '326'
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:
- '29999635'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_4caca47bc16bd9e3244cde87274121c3
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": "user", "content": "I
need to gather detailed information about AI to write an amazing paragraph.\n\nAction:
learn_about_AI\nAction Input: {}\nObservation: AI is a very broad field."},
{"role": "user", "content": "Thought: I need more specific and comprehensive
information on AI to craft an amazing paragraph.\n\nAction: learn_about_AI\nAction
Input: {}\nObservation: I tried reusing the same input, I must stop using this
action input. I''ll try something else instead.\n\n"}], "model": "gpt-4o", "stop":
["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1864'
content-type:
- application/json
cookie:
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.46.0
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-A8isfSuqZVE2UnV79ukPDSg0U8Dla\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642509,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: Since using empty inputs does
not yield specific results, I should focus on my understanding of AI and combine
it with detailed examples to craft an amazing paragraph.\\n\\nAction: learn_about_AI\\nAction
Input: {}\\n\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
369,\n \"completion_tokens\": 42,\n \"total_tokens\": 411,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_8dd226ca9c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6dc0da2fa67a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:55:09 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:
- '554'
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:
- '29999572'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_1b28842c322de09c15d01c2289fee4a8
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": "user", "content": "I
need to gather detailed information about AI to write an amazing paragraph.\n\nAction:
learn_about_AI\nAction Input: {}\nObservation: AI is a very broad field."},
{"role": "user", "content": "Thought: I need more specific and comprehensive
information on AI to craft an amazing paragraph.\n\nAction: learn_about_AI\nAction
Input: {}\nObservation: I tried reusing the same input, I must stop using this
action input. I''ll try something else instead.\n\n"}, {"role": "user", "content":
"Thought: Since using empty inputs does not yield specific results, I should
focus on my understanding of AI and combine it with detailed examples to craft
an amazing paragraph.\n\nAction: learn_about_AI\nAction Input: {}\n\nObservation:
I tried reusing the same input, I must stop using this action input. I''ll try
something else instead.\n\n\n\n\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"}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3053'
content-type:
- application/json
cookie:
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.46.0
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-A8isf4mgZ1K4q0TsCCbV0fbUPIoJi\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642509,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: To gather the best and most
comprehensive information about AI, I need to ensure the input for the tool
is clear and specific. This will help generate the required detailed information.\\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\": 613,\n \"completion_tokens\": 46,\n
\ \"total_tokens\": 659,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_8dd226ca9c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6dc64caaa67a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:55:10 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:
- '470'
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:
- '29999288'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_756b2e5e028bbfb1010f710e7c3109fa
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": "user", "content": "I
need to gather detailed information about AI to write an amazing paragraph.\n\nAction:
learn_about_AI\nAction Input: {}\nObservation: AI is a very broad field."},
{"role": "user", "content": "Thought: I need more specific and comprehensive
information on AI to craft an amazing paragraph.\n\nAction: learn_about_AI\nAction
Input: {}\nObservation: I tried reusing the same input, I must stop using this
action input. I''ll try something else instead.\n\n"}, {"role": "user", "content":
"Thought: Since using empty inputs does not yield specific results, I should
focus on my understanding of AI and combine it with detailed examples to craft
an amazing paragraph.\n\nAction: learn_about_AI\nAction Input: {}\n\nObservation:
I tried reusing the same input, I must stop using this action input. I''ll try
something else instead.\n\n\n\n\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": "Thought:
To gather the best and most comprehensive information about AI, I need to ensure
the input for the tool is clear and specific. This will help generate the required
detailed information.\n\nAction: learn_about_AI\nAction Input: {}\nObservation:
I tried reusing the same input, I must stop using this action input. I''ll try
something else instead.\n\n"}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3444'
content-type:
- application/json
cookie:
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.46.0
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-A8isgA8Az1GhfhG6WFWbFAZgDfgBl\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642510,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: Reusing the same empty input
does not yield specific information. Let me rethink my approach and come up
with a clear action input that can help me gain comprehensive details about
AI for writing a paragraph.\\n\\nAction: learn_about_AI\\nAction Input: {\\\"focus\\\":
\\\"overview of AI, its applications, and its impact on society\\\"}\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 687,\n \"completion_tokens\":
67,\n \"total_tokens\": 754,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_8dd226ca9c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6dcb2f37a67a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:55:11 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:
- '698'
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:
- '29999199'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_b806b53d21e8b15e7a07cb8ac81e1ef1
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": "user", "content": "I
need to gather detailed information about AI to write an amazing paragraph.\n\nAction:
learn_about_AI\nAction Input: {}\nObservation: AI is a very broad field."},
{"role": "user", "content": "Thought: I need more specific and comprehensive
information on AI to craft an amazing paragraph.\n\nAction: learn_about_AI\nAction
Input: {}\nObservation: I tried reusing the same input, I must stop using this
action input. I''ll try something else instead.\n\n"}, {"role": "user", "content":
"Thought: Since using empty inputs does not yield specific results, I should
focus on my understanding of AI and combine it with detailed examples to craft
an amazing paragraph.\n\nAction: learn_about_AI\nAction Input: {}\n\nObservation:
I tried reusing the same input, I must stop using this action input. I''ll try
something else instead.\n\n\n\n\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": "Thought:
To gather the best and most comprehensive information about AI, I need to ensure
the input for the tool is clear and specific. This will help generate the required
detailed information.\n\nAction: learn_about_AI\nAction Input: {}\nObservation:
I tried reusing the same input, I must stop using this action input. I''ll try
something else instead.\n\n"}, {"role": "user", "content": "Thought: Reusing
the same empty input does not yield specific information. Let me rethink my
approach and come up with a clear action input that can help me gain comprehensive
details about AI for writing a paragraph.\n\nAction: learn_about_AI\nAction
Input: {\"focus\": \"overview of AI, its applications, and its impact on society\"}\nObservation:
AI is a very broad field."}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3852'
content-type:
- application/json
cookie:
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.46.0
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-A8ish3cQhdHclBSU1BvU407pRYZhs\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642511,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I received a broader comment
about AI being a very broad field. I'll try a different approach to get more
detailed information about AI.\\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\": 767,\n \"completion_tokens\":
38,\n \"total_tokens\": 805,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_8dd226ca9c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6dd18ae2a67a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:55:12 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:
- '449'
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:
- '29999106'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_f6eb889d6c4b0ec7c87820799602eaf2
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": "user", "content": "I
need to gather detailed information about AI to write an amazing paragraph.\n\nAction:
learn_about_AI\nAction Input: {}\nObservation: AI is a very broad field."},
{"role": "user", "content": "Thought: I need more specific and comprehensive
information on AI to craft an amazing paragraph.\n\nAction: learn_about_AI\nAction
Input: {}\nObservation: I tried reusing the same input, I must stop using this
action input. I''ll try something else instead.\n\n"}, {"role": "user", "content":
"Thought: Since using empty inputs does not yield specific results, I should
focus on my understanding of AI and combine it with detailed examples to craft
an amazing paragraph.\n\nAction: learn_about_AI\nAction Input: {}\n\nObservation:
I tried reusing the same input, I must stop using this action input. I''ll try
something else instead.\n\n\n\n\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": "Thought:
To gather the best and most comprehensive information about AI, I need to ensure
the input for the tool is clear and specific. This will help generate the required
detailed information.\n\nAction: learn_about_AI\nAction Input: {}\nObservation:
I tried reusing the same input, I must stop using this action input. I''ll try
something else instead.\n\n"}, {"role": "user", "content": "Thought: Reusing
the same empty input does not yield specific information. Let me rethink my
approach and come up with a clear action input that can help me gain comprehensive
details about AI for writing a paragraph.\n\nAction: learn_about_AI\nAction
Input: {\"focus\": \"overview of AI, its applications, and its impact on society\"}\nObservation:
AI is a very broad field."}, {"role": "user", "content": "Thought: I received
a broader comment about AI being a very broad field. I''ll try a different approach
to get more detailed information about AI.\n\nAction: learn_about_AI\nAction
Input: {}\nObservation: AI is a very broad field.\n\n\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"}], "model": "gpt-4o", "stop":
["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '4928'
content-type:
- application/json
cookie:
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.46.0
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-A8isilwNtEyAdfnAjd6ZsjydTQbzo\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642512,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: My previous approach with empty
inputs hasn't worked. I need to provide a specific and clear input to get the
detailed information I need.\\n\\nAction: learn_about_AI\\nAction Input: {\\\"subject\\\":
\\\"overview, applications, and societal impact of AI\\\"}\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 992,\n \"completion_tokens\":
51,\n \"total_tokens\": 1043,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_8dd226ca9c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6dd66d39a67a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:55:13 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:
- '677'
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:
- '29998852'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_b9c2444e58d608e67e208c0e2f30a238
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": "user", "content": "I
need to gather detailed information about AI to write an amazing paragraph.\n\nAction:
learn_about_AI\nAction Input: {}\nObservation: AI is a very broad field."},
{"role": "user", "content": "Thought: I need more specific and comprehensive
information on AI to craft an amazing paragraph.\n\nAction: learn_about_AI\nAction
Input: {}\nObservation: I tried reusing the same input, I must stop using this
action input. I''ll try something else instead.\n\n"}, {"role": "user", "content":
"Thought: Since using empty inputs does not yield specific results, I should
focus on my understanding of AI and combine it with detailed examples to craft
an amazing paragraph.\n\nAction: learn_about_AI\nAction Input: {}\n\nObservation:
I tried reusing the same input, I must stop using this action input. I''ll try
something else instead.\n\n\n\n\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": "Thought:
To gather the best and most comprehensive information about AI, I need to ensure
the input for the tool is clear and specific. This will help generate the required
detailed information.\n\nAction: learn_about_AI\nAction Input: {}\nObservation:
I tried reusing the same input, I must stop using this action input. I''ll try
something else instead.\n\n"}, {"role": "user", "content": "Thought: Reusing
the same empty input does not yield specific information. Let me rethink my
approach and come up with a clear action input that can help me gain comprehensive
details about AI for writing a paragraph.\n\nAction: learn_about_AI\nAction
Input: {\"focus\": \"overview of AI, its applications, and its impact on society\"}\nObservation:
AI is a very broad field."}, {"role": "user", "content": "Thought: I received
a broader comment about AI being a very broad field. I''ll try a different approach
to get more detailed information about AI.\n\nAction: learn_about_AI\nAction
Input: {}\nObservation: AI is a very broad field.\n\n\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":
"Thought: My previous approach with empty inputs hasn''t worked. I need to provide
a specific and clear input to get the detailed information I need.\n\nAction:
learn_about_AI\nAction Input: {\"subject\": \"overview, applications, and societal
impact of AI\"}\nObservation: AI is a very broad field."}], "model": "gpt-4o",
"stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '5258'
content-type:
- application/json
cookie:
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.46.0
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-A8isjGRyz4zXuk7nhU4TGIeWPOoXk\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642513,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: Clearly, reusing the same input
without a significant change leads to the same broad response. However, I need
to gather comprehensive information about AI from scratch.\\n\\nAction: learn_about_AI\\nAction
Input: {\\\"subject\\\": \\\"detailed description of AI, its applications, and
its impact on various sectors such as healthcare, finance, and education.\\\"}\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 1056,\n \"completion_tokens\":
71,\n \"total_tokens\": 1127,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_8dd226ca9c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6ddc988aa67a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:55:14 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:
- '760'
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:
- '29998778'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_ee3ae4b7e3c9dbecf3e6934190b32084
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": "user", "content": "I
need to gather detailed information about AI to write an amazing paragraph.\n\nAction:
learn_about_AI\nAction Input: {}\nObservation: AI is a very broad field."},
{"role": "user", "content": "Thought: I need more specific and comprehensive
information on AI to craft an amazing paragraph.\n\nAction: learn_about_AI\nAction
Input: {}\nObservation: I tried reusing the same input, I must stop using this
action input. I''ll try something else instead.\n\n"}, {"role": "user", "content":
"Thought: Since using empty inputs does not yield specific results, I should
focus on my understanding of AI and combine it with detailed examples to craft
an amazing paragraph.\n\nAction: learn_about_AI\nAction Input: {}\n\nObservation:
I tried reusing the same input, I must stop using this action input. I''ll try
something else instead.\n\n\n\n\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": "Thought:
To gather the best and most comprehensive information about AI, I need to ensure
the input for the tool is clear and specific. This will help generate the required
detailed information.\n\nAction: learn_about_AI\nAction Input: {}\nObservation:
I tried reusing the same input, I must stop using this action input. I''ll try
something else instead.\n\n"}, {"role": "user", "content": "Thought: Reusing
the same empty input does not yield specific information. Let me rethink my
approach and come up with a clear action input that can help me gain comprehensive
details about AI for writing a paragraph.\n\nAction: learn_about_AI\nAction
Input: {\"focus\": \"overview of AI, its applications, and its impact on society\"}\nObservation:
AI is a very broad field."}, {"role": "user", "content": "Thought: I received
a broader comment about AI being a very broad field. I''ll try a different approach
to get more detailed information about AI.\n\nAction: learn_about_AI\nAction
Input: {}\nObservation: AI is a very broad field.\n\n\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":
"Thought: My previous approach with empty inputs hasn''t worked. I need to provide
a specific and clear input to get the detailed information I need.\n\nAction:
learn_about_AI\nAction Input: {\"subject\": \"overview, applications, and societal
impact of AI\"}\nObservation: AI is a very broad field."}, {"role": "user",
"content": "Thought: Clearly, reusing the same input without a significant change
leads to the same broad response. However, I need to gather comprehensive information
about AI from scratch.\n\nAction: learn_about_AI\nAction Input: {\"subject\":
\"detailed description of AI, its applications, and its impact on various sectors
such as healthcare, finance, and education.\"}\nObservation: AI is a very broad
field."}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '5693'
content-type:
- application/json
cookie:
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.46.0
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-A8iskTvZ9pNqWFvy1cxPRLSlwVgrq\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642514,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: Given that I am repeatedly receiving
a broad response from the tool, I need to formulate an amazing paragraph based
on my existing understanding and the broad information I have.\\n\\nThought:
I now know the final answer\\nFinal Answer: Artificial Intelligence (AI) is
a transformative force that is redefining various sectors including healthcare,
finance, and education. At its core, AI leverages computational algorithms to
mimic human intelligence, enabling machines to learn from data, recognize patterns,
and make decisions. In healthcare, AI is revolutionizing diagnostics and personalized
medicine, ensuring faster and more accurate treatment plans. The finance industry
benefits from AI through advanced fraud detection systems and automated trading
algorithms that optimize investment strategies. In education, AI-driven tools
are personalizing learning experiences, catering to individual student needs,
and enhancing educational outcomes. The societal impact of AI is immense, creating
more efficient systems and opening up new possibilities previously deemed unimaginable.
As AI continues to evolve, its potential to drive innovation and improve quality
of life across different domains remains boundless.\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 1140,\n \"completion_tokens\":
204,\n \"total_tokens\": 1344,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_8dd226ca9c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6de36c5fa67a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:55:16 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:
- '1946'
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:
- '29998679'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_fe31b6c95a292fd7291ed1a1c344d2dc
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink