andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-10 00:28:31 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
Files
0ab072a95ed08404260c841f97b706189ae161a7
crewAI/tests/cassettes/test_agent_function_calling_llm.yaml
João Moura 5a3b888f43 Updating all cassetes
2024-09-18 04:17:41 -03:00

842 lines
38 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-A8ismomOkOCa0xK3gepORDK4u6Glb\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642516,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I need to gather information about AI
to write an amazing paragraph. I will start by learning about AI using the available
tool.\\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\":
35,\n \"total_tokens\": 312,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_8dd226ca9c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6df1ab2fa67a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:55:17 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:
- '404'
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_de33b681dcd6050db50d688408de30f2
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:
- '2020'
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, 18 Sep 2024 06:55:17 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(*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 information about AI to write an amazing paragraph. I will start
by learning about AI using the available tool.\n\nAction: learn_about_AI\nAction
Input: {}\nObservation: You tried to use the tool <Mock name=''from_litellm().chat.completions.create().tool_name''
id=''6043100176''>, but it doesn''t exist. You must use one of the following
tools, use one at time: learn_about_ai."}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1800'
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-A8isnpPwGhiu8iq9z6EQIjnoqWKND\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642517,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I should use the correct tool,
which is \\\"learn_about_AI\\\" to gather 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\": 374,\n \"completion_tokens\": 32,\n
\ \"total_tokens\": 406,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_8dd226ca9c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6df63d3ea67a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:55:18 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=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999578'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_23a7c7bd2b4b6c0990f7cb78d68b365e
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 information about AI to write an amazing paragraph. I will start
by learning about AI using the available tool.\n\nAction: learn_about_AI\nAction
Input: {}\nObservation: You tried to use the tool <Mock name=''from_litellm().chat.completions.create().tool_name''
id=''6043100176''>, but it doesn''t exist. You must use one of the following
tools, use one at time: learn_about_ai."}, {"role": "user", "content": "Thought:
I should use the correct tool, which is \"learn_about_AI\" to gather information
about AI.\n\nAction: learn_about_AI\nAction Input: {}\nObservation: You tried
to use the tool <Mock name=''from_litellm().chat.completions.create().tool_name''
id=''6043100176''>, but it doesn''t exist. You must use one of the following
tools, use one at time: learn_about_ai.\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:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2368'
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-A8isoyHbw2B6bHkpLVmK2hA4fBsFQ\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642518,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Artificial Intelligence (AI) is a transformative
technology that leverages computational algorithms to perform tasks typically
requiring human intelligence. These tasks range from visual perception and speech
recognition to decision-making and language translation. AI systems can be classified
into narrow AI, which is designed for specific tasks, and general AI, which
has the capability to perform any intellectual task that a human can. The impact
of AI spans various industries, including healthcare, finance, and transportation,
driving advancements and efficiencies that were once thought impossible. As
AI continues to evolve, it holds the promise of revolutionizing the way we live
and work, but it also raises important ethical and societal considerations that
must be addressed.\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
500,\n \"completion_tokens\": 132,\n \"total_tokens\": 632,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_8dd226ca9c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6dfbafc1a67a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:55:19 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:
- '1369'
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:
- '29999446'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_0b3048a4925d48f1ca9a7e71992e8404
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 information about AI to write an amazing paragraph. I will start
by learning about AI using the available tool.\n\nAction: learn_about_AI\nAction
Input: {}\nObservation: You tried to use the tool <Mock name=''from_litellm().chat.completions.create().tool_name''
id=''6043100176''>, but it doesn''t exist. You must use one of the following
tools, use one at time: learn_about_ai."}, {"role": "user", "content": "Thought:
I should use the correct tool, which is \"learn_about_AI\" to gather information
about AI.\n\nAction: learn_about_AI\nAction Input: {}\nObservation: You tried
to use the tool <Mock name=''from_litellm().chat.completions.create().tool_name''
id=''6043100176''>, but it doesn''t exist. You must use one of the following
tools, use one at time: learn_about_ai.\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 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-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2802'
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-A8isqgQxCXt0Btte90UFDQEJkoc48\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642520,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I should gather information
about AI to craft an amazing paragraph. I will use the correct tool \\\"learn_about_AI\\\"
this time.\\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\": 594,\n \"completion_tokens\":
38,\n \"total_tokens\": 632,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_8dd226ca9c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6e065bf1a67a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:55:20 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:
- '490'
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:
- '29999347'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_74e88129349094240d86c1b1bb56982e
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 information about AI to write an amazing paragraph. I will start
by learning about AI using the available tool.\n\nAction: learn_about_AI\nAction
Input: {}\nObservation: You tried to use the tool <Mock name=''from_litellm().chat.completions.create().tool_name''
id=''6043100176''>, but it doesn''t exist. You must use one of the following
tools, use one at time: learn_about_ai."}, {"role": "user", "content": "Thought:
I should use the correct tool, which is \"learn_about_AI\" to gather information
about AI.\n\nAction: learn_about_AI\nAction Input: {}\nObservation: You tried
to use the tool <Mock name=''from_litellm().chat.completions.create().tool_name''
id=''6043100176''>, but it doesn''t exist. You must use one of the following
tools, use one at time: learn_about_ai.\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 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": "user", "content": "Thought: I should gather information
about AI to craft an amazing paragraph. I will use the correct tool \"learn_about_AI\"
this time.\n\nAction: learn_about_AI\nAction Input: {}\nObservation: You tried
to use the tool <Mock name=''from_litellm().chat.completions.create().tool_name''
id=''6043100176''>, but it doesn''t exist. You must use one of the following
tools, use one at time: learn_about_ai."}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3231'
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-A8isrzJUKbtyuVOeML4a3bDaSzGhP\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642521,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I should attempt to use the
correct format and tool one more time to gather the necessary 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\": 694,\n \"completion_tokens\":
33,\n \"total_tokens\": 727,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_8dd226ca9c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6e0b6e0ea67a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:55:21 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:
- '501'
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:
- '29999248'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_a57bad21c61fd89be1ab84b15e0aa1a8
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 information about AI to write an amazing paragraph. I will start
by learning about AI using the available tool.\n\nAction: learn_about_AI\nAction
Input: {}\nObservation: You tried to use the tool <Mock name=''from_litellm().chat.completions.create().tool_name''
id=''6043100176''>, but it doesn''t exist. You must use one of the following
tools, use one at time: learn_about_ai."}, {"role": "user", "content": "Thought:
I should use the correct tool, which is \"learn_about_AI\" to gather information
about AI.\n\nAction: learn_about_AI\nAction Input: {}\nObservation: You tried
to use the tool <Mock name=''from_litellm().chat.completions.create().tool_name''
id=''6043100176''>, but it doesn''t exist. You must use one of the following
tools, use one at time: learn_about_ai.\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 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": "user", "content": "Thought: I should gather information
about AI to craft an amazing paragraph. I will use the correct tool \"learn_about_AI\"
this time.\n\nAction: learn_about_AI\nAction Input: {}\nObservation: You tried
to use the tool <Mock name=''from_litellm().chat.completions.create().tool_name''
id=''6043100176''>, but it doesn''t exist. You must use one of the following
tools, use one at time: learn_about_ai."}, {"role": "user", "content": "Thought:
I should attempt to use the correct format and tool one more time to gather
the necessary information about AI.\n\nAction: learn_about_AI\nAction Input:
{}\nObservation: You tried to use the tool <Mock name=''from_litellm().chat.completions.create().tool_name''
id=''6043100176''>, but it doesn''t exist. You must use one of the following
tools, use one at time: learn_about_ai."}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3646'
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-A8isrKE5PWBc1f7LiEZ2S99i7Dvcs\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642521,\n \"model\": \"gpt-4o-2024-05-13\",\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 a transformative technology that has
the potential to revolutionize various aspects of our everyday lives. By simulating
human intelligence in machines, AI is capable of performing tasks that typically
require human intelligence, such as visual perception, speech recognition, decision-making,
and language translation. AI systems learn and adapt through algorithms and
vast amounts of data, enabling them to improve their performance over time.
As AI continues to advance, it holds promise for driving innovation across numerous
industries, including healthcare, finance, transportation, and entertainment,
ultimately enhancing efficiency, accuracy, and productivity.\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 789,\n \"completion_tokens\":
128,\n \"total_tokens\": 917,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_8dd226ca9c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c4f6e10888da67a-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 18 Sep 2024 06:55:23 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:
- '1388'
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:
- '29999153'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_8f45ac955d3324802003b0de7147c91a
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink