andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-09 08:08:32 +00:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity
Files
e77442cf3414d963c89464e4b5cd12b8104985bb
crewAI/tests/cassettes/test_agent_repeated_tool_usage.yaml
João Moura e77442cf34 Removing LangChain and Rebuilding Executor (#1322) 
* rebuilding executor

* removing langchain

* Making all tests good

* fixing types and adding ability for nor using system prompts

* improving types

* pleasing the types gods

* pleasing the types gods

* fixing parser, tools and executor

* making sure all tests pass

* final pass

* fixing type

* Updating Docs

* preparing to cut new version
2024-09-16 14:14:04 -03:00

627 lines
27 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: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \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 [get_final_answer],
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: The final answer is 42. But don''t give it until I tell you
so, instead keep using the `get_final_answer` tool.\n\nThis is the expect criteria
for your final answer: The final answer, don''t give it until I tell you so\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-4", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1467'
content-type:
- application/json
cookie:
- __cf_bm=1SckBhvJ18Dazp6bi8DEKYeiS9Q4.6_6i3nmLBw9b6g-1726476036-1.0.1.1-TnN4UpDXA33YXCVCUWOaZ12vGIg_o5NpJQEUHgjn6XdUgb7M0ND8PdkTfkd8rrxG5XFlPRMzI54GxZ0FeUY9xw;
_cfuvid=0Rs4xTPk7h7OIXuSbTgMVVD9JSoZeKMwnygKHoHQo3k-1726476036297-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A81cWlVtV5ekOB5c9azdzBW40yEFC\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476216,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I need to use the `get_final_answer`
tool to generate the final answer but I should not give the final answer yet.
I will use the tool constantly until I am told to provide the final response.\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 308,\n \"completion_tokens\":
42,\n \"total_tokens\": 350,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f91e2e8d62233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:43:39 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:
- '2141'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '1000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '999653'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 20ms
x-request-id:
- req_92057a976dd36d0b40261eb3603f4971
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: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \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 [get_final_answer],
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: The final answer is 42. But don''t give it until I tell you
so, instead keep using the `get_final_answer` tool.\n\nThis is the expect criteria
for your final answer: The final answer, don''t give it until I tell you so\nyou
MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}, {"role": "assistant", "content":
"I 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 satisfy the expect 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"}], "model": "gpt-4", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1906'
content-type:
- application/json
cookie:
- __cf_bm=1SckBhvJ18Dazp6bi8DEKYeiS9Q4.6_6i3nmLBw9b6g-1726476036-1.0.1.1-TnN4UpDXA33YXCVCUWOaZ12vGIg_o5NpJQEUHgjn6XdUgb7M0ND8PdkTfkd8rrxG5XFlPRMzI54GxZ0FeUY9xw;
_cfuvid=0Rs4xTPk7h7OIXuSbTgMVVD9JSoZeKMwnygKHoHQo3k-1726476036297-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A81cZcHeshIeHD88EFdOWuwEQcQRE\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476219,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I need to keep using the `get_final_answer`
tool until told otherwise. However, I don't have any specific input for the
tool at the moment. \\nAction: get_final_answer\\nAction Input: {}\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 405,\n \"completion_tokens\":
43,\n \"total_tokens\": 448,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f91f21cf02233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:43:41 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:
- '1965'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '1000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '999553'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 26ms
x-request-id:
- req_7f85a269238f0bef62e175fc1c8fd9d3
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: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \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 [get_final_answer],
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: The final answer is 42. But don''t give it until I tell you
so, instead keep using the `get_final_answer` tool.\n\nThis is the expect criteria
for your final answer: The final answer, don''t give it until I tell you so\nyou
MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}, {"role": "assistant", "content":
"I 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 satisfy the expect 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 need to keep using the
`get_final_answer` tool until told otherwise. However, I don''t have any specific
input for the tool at the moment. \nAction: get_final_answer\nAction Input:
{}\nObservation: 42"}], "model": "gpt-4", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2145'
content-type:
- application/json
cookie:
- __cf_bm=1SckBhvJ18Dazp6bi8DEKYeiS9Q4.6_6i3nmLBw9b6g-1726476036-1.0.1.1-TnN4UpDXA33YXCVCUWOaZ12vGIg_o5NpJQEUHgjn6XdUgb7M0ND8PdkTfkd8rrxG5XFlPRMzI54GxZ0FeUY9xw;
_cfuvid=0Rs4xTPk7h7OIXuSbTgMVVD9JSoZeKMwnygKHoHQo3k-1726476036297-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A81cbdMi0Ptxq4heqiAPKADCy9HYI\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476221,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I got the answer as 42 from
the tool. However, the task explicitly stated that I shouldn't give the answer
until told. Therefore, I need to keep using the `get_final_answer` tool.\\nAction:
get_final_answer\\nAction Input: {}\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 457,\n \"completion_tokens\": 54,\n
\ \"total_tokens\": 511,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f9200496e2233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:43:44 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:
- '2736'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '1000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '999503'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 29ms
x-request-id:
- req_ceecd9fba3a93a5e09b7bcea992c6299
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: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \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 [get_final_answer],
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: The final answer is 42. But don''t give it until I tell you
so, instead keep using the `get_final_answer` tool.\n\nThis is the expect criteria
for your final answer: The final answer, don''t give it until I tell you so\nyou
MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}, {"role": "assistant", "content":
"I 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 satisfy the expect 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 need to keep using the
`get_final_answer` tool until told otherwise. However, I don''t have any specific
input for the tool at the moment. \nAction: get_final_answer\nAction Input:
{}\nObservation: 42"}, {"role": "assistant", "content": "Thought: I got the
answer as 42 from the tool. However, the task explicitly stated that I shouldn''t
give the answer until told. Therefore, I need to keep using the `get_final_answer`
tool.\nAction: get_final_answer\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-4", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2535'
content-type:
- application/json
cookie:
- __cf_bm=1SckBhvJ18Dazp6bi8DEKYeiS9Q4.6_6i3nmLBw9b6g-1726476036-1.0.1.1-TnN4UpDXA33YXCVCUWOaZ12vGIg_o5NpJQEUHgjn6XdUgb7M0ND8PdkTfkd8rrxG5XFlPRMzI54GxZ0FeUY9xw;
_cfuvid=0Rs4xTPk7h7OIXuSbTgMVVD9JSoZeKMwnygKHoHQo3k-1726476036297-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A81cezl6pjhfjS47BWUbFtXHdnOsz\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476224,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I am not sure whether to provide
the final answer yet since the task specifies to not give the answer until told.
I should continue using the `get_final_answer` tool.\\nAction: get_final_answer\\nAction
Input: {}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
541,\n \"completion_tokens\": 47,\n \"total_tokens\": 588,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f9213d82f2233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:43:47 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:
- '2451'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '1000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '999415'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 35ms
x-request-id:
- req_8d350f93e97fc2ecb9b9df5975dc3b2b
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: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \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 [get_final_answer],
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: The final answer is 42. But don''t give it until I tell you
so, instead keep using the `get_final_answer` tool.\n\nThis is the expect criteria
for your final answer: The final answer, don''t give it until I tell you so\nyou
MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}, {"role": "assistant", "content":
"I 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 satisfy the expect 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 need to keep using the
`get_final_answer` tool until told otherwise. However, I don''t have any specific
input for the tool at the moment. \nAction: get_final_answer\nAction Input:
{}\nObservation: 42"}, {"role": "assistant", "content": "Thought: I got the
answer as 42 from the tool. However, the task explicitly stated that I shouldn''t
give the answer until told. Therefore, I need to keep using the `get_final_answer`
tool.\nAction: get_final_answer\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": "assistant", "content": "Thought: I am not sure whether
to provide the final answer yet since the task specifies to not give the answer
until told. I should continue using the `get_final_answer` tool.\nAction: get_final_answer\nAction
Input: {}\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: get_final_answer(*args: Any, **kwargs: Any) -> Any\nTool Description:
get_final_answer() - Get the final answer but don''t give it yet, just re-use
this tool non-stop. \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 [get_final_answer], 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\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-4", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3915'
content-type:
- application/json
cookie:
- __cf_bm=1SckBhvJ18Dazp6bi8DEKYeiS9Q4.6_6i3nmLBw9b6g-1726476036-1.0.1.1-TnN4UpDXA33YXCVCUWOaZ12vGIg_o5NpJQEUHgjn6XdUgb7M0ND8PdkTfkd8rrxG5XFlPRMzI54GxZ0FeUY9xw;
_cfuvid=0Rs4xTPk7h7OIXuSbTgMVVD9JSoZeKMwnygKHoHQo3k-1726476036297-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A81chmZnwAdzXb96fOTgZgdjGhh4u\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476227,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now know the final answer\\nFinal
Answer: The final answer is 42.\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
832,\n \"completion_tokens\": 19,\n \"total_tokens\": 851,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f92250d632233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:43:48 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:
- '987'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '1000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '999085'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 54ms
x-request-id:
- req_ffa5c2ca63f4ed556210071b071ce72b
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink