andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-24 23:58:15 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
Files
3cd464497b26ae499d46ddfda0eb92a294051cbe
crewAI/tests/cassettes/test_output_json_hierarchical.yaml
João Moura 3cd464497b rebuilding executor
2024-09-13 04:38:19 -05:00

509 lines
22 KiB
YAML
Raw Blame History

interactions:
- request:
body: '{"messages": [{"role": "user", "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\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. \n you 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:
- '2980'
content-type:
- application/json
cookie:
- _cfuvid=8r8yFLG2b7e3n6pklgpsT05MHRvfdePz1ckAFvRQY8E-1725949790252-0.0.1.1-604800000;
__cf_bm=fuuc.ZDO3Y9B7nXE_8fBn7ykDAvAaK1VdxjZw0MTtsE-1725949790-1.0.1.1-pAJ7BWJMj1j3gS2ySR6xSBO7uFrjcB6ehFra4QVq14JqaiG4VDIjDO1C3WueKGRnSALSkpLQyJcJ2YVd_pXglQ
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A5oiGZtyGVDA0w9otj9rbpbQg03km\",\n \"object\":
\"chat.completion\",\n \"created\": 1725949944,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"To determine the appropriate score for
the title \\\"The impact of AI in the future of work,\\\" I need to involve
our Scorer. I will delegate the task to them with detailed context to ensure
they provide an accurate score.\\n\\nAction: Delegate work to coworker\\nAction
Input: {\\\"task\\\": \\\"Give an integer score between 1-5 for the following
title: 'The impact of AI in the future of work'\\\", \\\"context\\\": \\\"We
need to score the title based on its relevance, clarity, and appeal. A score
of 1 means the title is poor, while a score of 5 means the title is excellent.
Consider factors like how well the title encapsulates a relevant and engaging
topic.\\\", \\\"coworker\\\": \\\"Scorer\\\"}\\n\",\n \"refusal\": null\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 660,\n \"completion_tokens\":
152,\n \"total_tokens\": 812\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c0d61704856cf35-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 10 Sep 2024 06:32:26 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:
- '1819'
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:
- '29999270'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_6097fa7f18f573d36a8c58d387e6b174
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "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!\nCurrent Task: Give 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: Your best answer to your coworker
asking you this, accounting for the context shared. \n you MUST return the actual
complete content as the final answer, not a summary.\n\nThis is the context
you''re working with:\nWe need to score the title based on its relevance, clarity,
and appeal. A score of 1 means the title is poor, while a score of 5 means the
title is excellent. Consider factors like how well the title encapsulates a
relevant and engaging topic.\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:
- '1257'
content-type:
- application/json
cookie:
- _cfuvid=8r8yFLG2b7e3n6pklgpsT05MHRvfdePz1ckAFvRQY8E-1725949790252-0.0.1.1-604800000;
__cf_bm=fuuc.ZDO3Y9B7nXE_8fBn7ykDAvAaK1VdxjZw0MTtsE-1725949790-1.0.1.1-pAJ7BWJMj1j3gS2ySR6xSBO7uFrjcB6ehFra4QVq14JqaiG4VDIjDO1C3WueKGRnSALSkpLQyJcJ2YVd_pXglQ
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A5oiJ9AHm2wZYXheSKPeTFKrUmR29\",\n \"object\":
\"chat.completion\",\n \"created\": 1725949947,\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: 4\\n\\nThe title 'The impact of AI in the future of work' scores a 4.
It is highly relevant, as artificial intelligence is a significant and timely
topic affecting various aspects of work and industry. The title is clear and
concise, immediately indicating the focus on AI's role in shaping future work
environments. It is appealing because it touches on both technology and its
implications, which are pertinent to a wide audience. However, it could be slightly
more specific to achieve a perfect score.\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 254,\n \"completion_tokens\": 112,\n
\ \"total_tokens\": 366\n },\n \"system_fingerprint\": \"fp_157b3831f5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c0d61804a17cf35-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 10 Sep 2024 06:32:28 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:
- '1550'
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:
- '29999696'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_846b42e87a818ed85d04450086d6e2e2
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "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\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. \n you 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": "To determine the appropriate score for the title \"The
impact of AI in the future of work,\" I need to involve our Scorer. I will delegate
the task to them with detailed context to ensure they provide an accurate score.\n\nAction:
Delegate work to coworker\nAction Input: {\"task\": \"Give an integer score
between 1-5 for the following title: ''The impact of AI in the future of work''\",
\"context\": \"We need to score the title based on its relevance, clarity, and
appeal. A score of 1 means the title is poor, while a score of 5 means the title
is excellent. Consider factors like how well the title encapsulates a relevant
and engaging topic.\", \"coworker\": \"Scorer\"}\n\nObservation: 4\n\nThe title
''The impact of AI in the future of work'' scores a 4. It is highly relevant,
as artificial intelligence is a significant and timely topic affecting various
aspects of work and industry. The title is clear and concise, immediately indicating
the focus on AI''s role in shaping future work environments. It is appealing
because it touches on both technology and its implications, which are pertinent
to a wide audience. However, it could be slightly more specific to achieve a
perfect score."}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '4212'
content-type:
- application/json
cookie:
- _cfuvid=8r8yFLG2b7e3n6pklgpsT05MHRvfdePz1ckAFvRQY8E-1725949790252-0.0.1.1-604800000;
__cf_bm=fuuc.ZDO3Y9B7nXE_8fBn7ykDAvAaK1VdxjZw0MTtsE-1725949790-1.0.1.1-pAJ7BWJMj1j3gS2ySR6xSBO7uFrjcB6ehFra4QVq14JqaiG4VDIjDO1C3WueKGRnSALSkpLQyJcJ2YVd_pXglQ
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A5oiLXBB53MvwRHVSPLYlQhvMsKBU\",\n \"object\":
\"chat.completion\",\n \"created\": 1725949949,\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\":
917,\n \"completion_tokens\": 14,\n \"total_tokens\": 931\n },\n \"system_fingerprint\":
\"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c0d618bd907cf35-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 10 Sep 2024 06:32:29 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:
- '276'
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:
- '29998974'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_8f1a7115d850a517128e4a5d2ebac10f
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.\n\nThe json should have the
following structure, with the following keys:\n{\n score: int\n}"}], "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:
- '615'
content-type:
- application/json
cookie:
- __cf_bm=B5UEX82SlhFAhiEbobEv42vqC_s0jiOE9..GEHd2PM8-1725949937-1.0.1.1-jazIEvwLe8YXt0Xldxw5V3Dm50joI_ajSaDngSFCWqVdgRm3rJxeYip55y1JxFf90tlPQWlc28VZLg5QpQUNcA;
_cfuvid=yMG4HwMFIQbW20zb7f_ElvINxRtWnRbaaUVp1YqP5vY-1725949937391-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
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-A5oiLauxef1zJZb7fZgwa54LZx0UV\",\n \"object\":
\"chat.completion\",\n \"created\": 1725949949,\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_6v3iTXG0u3Hneuvq148KaGga\",\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\":
100,\n \"completion_tokens\": 5,\n \"total_tokens\": 105\n },\n \"system_fingerprint\":
\"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c0d6192580e17e8-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 10 Sep 2024 06:32:30 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:
- '171'
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:
- '29999947'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_09241c40c367f00f3803552b1c1c5be7
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink