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
539b910d7d173c73e326f0f0ba9ce3cd5317f0a7
crewAI/tests/cassettes/test_output_json_hierarchical.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

582 lines
26 KiB
YAML
Raw Blame History

interactions:
- request:
body: !!binary |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:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '2619'
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:
- Mon, 16 Sep 2024 08:51:52 GMT
status:
code: 200
message: OK
- 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", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3014'
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-A81kV26scB4k0y0IDwKfP9TZqkQK9\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476711,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"To assign a score between 1-5 for the
given title, 'The impact of AI in the future of work,' we need an expert evaluation
from Scorer. Therefore, I should delegate this task to Scorer with all necessary
context.\\n\\nAction: Delegate work to coworker\\nAction Input: {\\\"task\\\":
\\\"Assign an integer score between 1-5 to the title 'The impact of AI in the
future of work'.\\\", \\\"context\\\": \\\"This score should be based on criteria
like relevance, clarity, and the potential interest it might generate.\\\",
\\\"coworker\\\": \\\"Scorer\\\"}\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 664,\n \"completion_tokens\": 121,\n
\ \"total_tokens\": 785,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f9df4cd7d2233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:51:53 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:
- '1664'
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_63698d58a30663095f5f0992b7e7b099
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: Assign an integer score between 1-5 to 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:\nThis
score should be based on criteria like relevance, clarity, and the potential
interest it might generate.\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:
- '1148'
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-A81kXP9ayLKy8TKNaCROUb6q2ZAK8\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476713,\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. The title 'The impact of AI in the future of work' is highly relevant
given the current rapid advancements in artificial intelligence and its increasing
influence on various industries. It is clear and direct, making it easy to understand.
Additionally, it has the potential to generate significant interest as many
people are keen to understand how AI will affect job markets, employment opportunities,
and work practices in the future. However, while it is strong, it isn't exceptionally
unique, hence not a full score of 5.\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 222,\n \"completion_tokens\": 115,\n
\ \"total_tokens\": 337,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f9e0439222233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:51:55 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:
- '1382'
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:
- '29999730'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_f869e9c3635fce7c71f3ebcb4fc7c8ae
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": "assistant", "content": "To assign a score between
1-5 for the given title, ''The impact of AI in the future of work,'' we need
an expert evaluation from Scorer. Therefore, I should delegate this task to
Scorer with all necessary context.\n\nAction: Delegate work to coworker\nAction
Input: {\"task\": \"Assign an integer score between 1-5 to the title ''The impact
of AI in the future of work''.\", \"context\": \"This score should be based
on criteria like relevance, clarity, and the potential interest it might generate.\",
\"coworker\": \"Scorer\"}\nObservation: 4. The title ''The impact of AI in the
future of work'' is highly relevant given the current rapid advancements in
artificial intelligence and its increasing influence on various industries.
It is clear and direct, making it easy to understand. Additionally, it has the
potential to generate significant interest as many people are keen to understand
how AI will affect job markets, employment opportunities, and work practices
in the future. However, while it is strong, it isn''t exceptionally unique,
hence not a full score of 5."}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '4120'
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-A81kZNgpEtJkPq3YYSeVdAG8L2xGM\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476715,\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\":
893,\n \"completion_tokens\": 14,\n \"total_tokens\": 907,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f9e0f2ba62233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:51:56 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:
- '265'
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:
- '29999005'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_b061191d82b30670c32a78b1f1c36ace
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=04EJuO0mh2HU6FxLd2CpOc6Z6MMpyxhMCz_t6onOpaY-1726476704-1.0.1.1-BHP4W7X58z8ba4ns2wYBcPx53or5JKBDisMn8i7dQluTmjuN201bym7OqEkZrmUlhr0n3oODNJf0SS5BVipRKg;
_cfuvid=JBsdqQQtLEVtIStEIeDR0TRIr0GMGhWKAyum6suoH.4-1726476704561-0.0.1.1-604800000
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-A81kaLvjl5BI4M49jFqtDkiYMnIL8\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476716,\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_WfxcEVNESfq7erAWLUejB6Fh\",\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_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f9e180fc97494-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:51:57 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:
- '175'
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_8ae31fcf926453ca60ac3e71a738f0d2
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink