andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-10 16:48:30 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity
Files
59e51f18fd43b154c1068d74c2f88d754bc20f10
crewAI/tests/cassettes/test_output_json_hierarchical.yaml
João Moura 59e51f18fd updating tests
2024-09-23 03:58:41 -03:00

497 lines
22 KiB
YAML
Raw Blame History

interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
are a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Delegate work to coworker(task: str, context:
str, coworker: Optional[str] = None, **kwargs)\nTool Description: Delegate a
specific task to one of the following coworkers: Scorer\nThe input to this tool
should be the coworker, the task you want them to do, and ALL necessary context
to execute the task, they know nothing about the task, so share absolute everything
you know, don''t reference things but instead explain them.\nTool Arguments:
{''task'': {''title'': ''Task'', ''type'': ''string''}, ''context'': {''title'':
''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'',
''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\nTool
Name: Ask question to coworker(question: str, context: str, coworker: Optional[str]
= None, **kwargs)\nTool Description: Ask a specific question to one of the following
coworkers: Scorer\nThe input to this tool should be the coworker, the question
you have for them, and ALL necessary context to ask the question properly, they
know nothing about the question, so share absolute everything you know, don''t
reference things but instead explain them.\nTool Arguments: {''question'': {''title'':
''Question'', ''type'': ''string''}, ''context'': {''title'': ''Context'', ''type'':
''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''},
''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, only one name of [Delegate work to coworker, Ask question to coworker],
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: Give me an integer score between 1-5 for the following title:
''The impact of AI in the future of work''\n\nThis is the expect criteria for
your final answer: The score of the title.\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"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2986'
content-type:
- application/json
cookie:
- __cf_bm=hYfEMfBWpIoRPjx9ZBZg6DVeMOMr1IZt9ioup8yWZs0-1727072673-1.0.1.1-Ro7GCLuWS0K5ob0mSTYSmovONKNyxsK6oSA5io_Vwqhe6P0G7Ow4CuZUaWAaCdFGQUd7XZiFH0mI_sQC3uqe0g;
_cfuvid=5cK2hfLqTXw1WjB81uT.sGmmA67JIxSKSQeEHQ3zOQw-1727071769966-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
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-AAWsFiDTK2q7CWPuBBBKr2RqNmTXK\",\n \"object\":
\"chat.completion\",\n \"created\": 1727073011,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"To provide an accurate and informed integer
score for the title \\\"The impact of AI in the future of work,\\\" I need to
delegate the task to the Scorer, who has the expertise to rate the title based
on specific criteria.\\n\\nAction: Delegate work to coworker\\nAction Input:
{\\\"task\\\": \\\"Give an integer score between 1-5 for the title 'The impact
of AI in the future of work'\\\", \\\"context\\\": \\\"Please evaluate the provided
title based on clarity, relevance, and potential interest to the audience. The
score should be within the range of 1-5, where 1 is the lowest and 5 is the
highest.\\\", \\\"coworker\\\": \\\"Scorer\\\"}\",\n \"refusal\": null\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 664,\n \"completion_tokens\":
141,\n \"total_tokens\": 805,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c787c107c79a4ee-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 23 Sep 2024 06:30:13 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:
- '1990'
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:
- '29999269'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_0be11a8904611f3d98497dfe5b86f92b
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are Scorer. You''re an
expert scorer, specialized in scoring titles.\nYour personal goal is: Score
the title\nTo give my best complete final answer to the task use the exact following
format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
answer must be the great and the most complete as possible, it must be outcome
described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
"content": "\nCurrent Task: Give an integer score between 1-5 for the title
''The impact of AI in the future of work''\n\nThis is the expect criteria for
your final answer: Your best answer to your coworker asking you this, accounting
for the context shared.\nyou MUST return the actual complete content as the
final answer, not a summary.\n\nThis is the context you''re working with:\nPlease
evaluate the provided title based on clarity, relevance, and potential interest
to the audience. The score should be within the range of 1-5, where 1 is the
lowest and 5 is the highest.\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"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1201'
content-type:
- application/json
cookie:
- __cf_bm=hYfEMfBWpIoRPjx9ZBZg6DVeMOMr1IZt9ioup8yWZs0-1727072673-1.0.1.1-Ro7GCLuWS0K5ob0mSTYSmovONKNyxsK6oSA5io_Vwqhe6P0G7Ow4CuZUaWAaCdFGQUd7XZiFH0mI_sQC3uqe0g;
_cfuvid=5cK2hfLqTXw1WjB81uT.sGmmA67JIxSKSQeEHQ3zOQw-1727071769966-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
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-AAWsISsMmeaS4l2iu0cWreiasi4MD\",\n \"object\":
\"chat.completion\",\n \"created\": 1727073014,\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: I would score the title 'The impact of AI in the future of
work' a 4. The title is clear, highly relevant in today's context, and likely
to attract significant interest from an audience interested in technology and
labor market trends.\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
246,\n \"completion_tokens\": 61,\n \"total_tokens\": 307,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_52a7f40b0b\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c787c1f2c2ba4ee-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 23 Sep 2024 06:30:14 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '649'
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:
- '29999711'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_dd7be23cc15020f3d6a3659d0b9f08f1
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
are a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Delegate work to coworker(task: str, context:
str, coworker: Optional[str] = None, **kwargs)\nTool Description: Delegate a
specific task to one of the following coworkers: Scorer\nThe input to this tool
should be the coworker, the task you want them to do, and ALL necessary context
to execute the task, they know nothing about the task, so share absolute everything
you know, don''t reference things but instead explain them.\nTool Arguments:
{''task'': {''title'': ''Task'', ''type'': ''string''}, ''context'': {''title'':
''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'',
''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\nTool
Name: Ask question to coworker(question: str, context: str, coworker: Optional[str]
= None, **kwargs)\nTool Description: Ask a specific question to one of the following
coworkers: Scorer\nThe input to this tool should be the coworker, the question
you have for them, and ALL necessary context to ask the question properly, they
know nothing about the question, so share absolute everything you know, don''t
reference things but instead explain them.\nTool Arguments: {''question'': {''title'':
''Question'', ''type'': ''string''}, ''context'': {''title'': ''Context'', ''type'':
''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''},
''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, only one name of [Delegate work to coworker, Ask question to coworker],
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: Give me an integer score between 1-5 for the following title:
''The impact of AI in the future of work''\n\nThis is the expect criteria for
your final answer: The score of the title.\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": "To provide an accurate and
informed integer score for the title \"The impact of AI in the future of work,\"
I need to delegate the task to the Scorer, who has the expertise to rate the
title based on specific criteria.\n\nAction: Delegate work to coworker\nAction
Input: {\"task\": \"Give an integer score between 1-5 for the title ''The impact
of AI in the future of work''\", \"context\": \"Please evaluate the provided
title based on clarity, relevance, and potential interest to the audience. The
score should be within the range of 1-5, where 1 is the lowest and 5 is the
highest.\", \"coworker\": \"Scorer\"}\nObservation: I would score the title
''The impact of AI in the future of work'' a 4. The title is clear, highly relevant
in today''s context, and likely to attract significant interest from an audience
interested in technology and labor market trends."}], "model": "gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3881'
content-type:
- application/json
cookie:
- __cf_bm=hYfEMfBWpIoRPjx9ZBZg6DVeMOMr1IZt9ioup8yWZs0-1727072673-1.0.1.1-Ro7GCLuWS0K5ob0mSTYSmovONKNyxsK6oSA5io_Vwqhe6P0G7Ow4CuZUaWAaCdFGQUd7XZiFH0mI_sQC3uqe0g;
_cfuvid=5cK2hfLqTXw1WjB81uT.sGmmA67JIxSKSQeEHQ3zOQw-1727071769966-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
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-AAWsJQZ6tiG5Wn5OS1f6lC8fiDmou\",\n \"object\":
\"chat.completion\",\n \"created\": 1727073015,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now know the final answer.\\nFinal
Answer: 4\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
859,\n \"completion_tokens\": 14,\n \"total_tokens\": 873,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c787c27887fa4ee-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 23 Sep 2024 06:30:15 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:
- '323'
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:
- '29999057'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_c6af70b0b22036aa59ffefb78d4d891d
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "4"}, {"role": "system", "content":
"I''m gonna convert this raw text into valid JSON."}], "model": "gpt-4o", "tool_choice":
{"type": "function", "function": {"name": "ScoreOutput"}}, "tools": [{"type":
"function", "function": {"name": "ScoreOutput", "description": "Correctly extracted
`ScoreOutput` with all the required parameters with correct types", "parameters":
{"properties": {"score": {"title": "Score", "type": "integer"}}, "required":
["score"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '519'
content-type:
- application/json
cookie:
- __cf_bm=hYfEMfBWpIoRPjx9ZBZg6DVeMOMr1IZt9ioup8yWZs0-1727072673-1.0.1.1-Ro7GCLuWS0K5ob0mSTYSmovONKNyxsK6oSA5io_Vwqhe6P0G7Ow4CuZUaWAaCdFGQUd7XZiFH0mI_sQC3uqe0g;
_cfuvid=5cK2hfLqTXw1WjB81uT.sGmmA67JIxSKSQeEHQ3zOQw-1727071769966-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
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-AAWsJBtKDowpdUQrGnrfcrTOjN3JL\",\n \"object\":
\"chat.completion\",\n \"created\": 1727073015,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_bVwltHPXi66CP0oTYVwtsLg3\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"ScoreOutput\",\n
\ \"arguments\": \"{\\\"score\\\":4}\"\n }\n }\n
\ ],\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
80,\n \"completion_tokens\": 5,\n \"total_tokens\": 85,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c787c2c7adda4ee-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 23 Sep 2024 06:30:16 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '189'
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:
- '29999968'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_7de4d70bd6e134a9298a55e37fc908e1
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink