Files
crewAI/tests/cassettes/test_increment_delegations_for_sequential_process.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

378 lines
17 KiB
YAML

interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Manager. You''re great
at delegating work about scoring.\nYour personal goal is: Coordinate scoring
processes\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:
- '2641'
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-A81l8X2YQ0TtLiK8jDndhlyHEJJBX\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476750,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"To provide an accurate score for the
title, I need to delegate the task to the Scorer with all necessary context.\\n\\nAction:
Delegate work to coworker\\nAction Input: {\\n \\\"coworker\\\": \\\"Scorer\\\",
\\n \\\"task\\\": \\\"Provide an integer score between 1-5 for the following
title: 'The impact of AI in the future of work'\\\",\\n \\\"context\\\":
\\\"The score should reflect how compelling and relevant the title is regarding
the integration and impact of Artificial Intelligence on future work scenarios.\\\"\\n}\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 584,\n \"completion_tokens\":
107,\n \"total_tokens\": 691,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f9ee7efeb2233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:52:31 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:
- '1342'
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:
- '29999361'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_2e50a53cea35304479bf2471a6a1ef58
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: Provide 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.\nyou MUST return the actual complete content as the
final answer, not a summary.\n\nThis is the context you''re working with:\nThe
score should reflect how compelling and relevant the title is regarding the
integration and impact of Artificial Intelligence on future work scenarios.\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:
- '1206'
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-A81l9KA2dKXdw8jJrkcxKhWo5C6qT\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476751,\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 \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
228,\n \"completion_tokens\": 15,\n \"total_tokens\": 243,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f9ef24a902233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:52:32 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:
- '314'
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:
- '29999717'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_fa9e1407947c78169d0f8b70f031f80c
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are Manager. You''re great
at delegating work about scoring.\nYour personal goal is: Coordinate scoring
processes\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 provide an accurate
score for the title, I need to delegate the task to the Scorer with all necessary
context.\n\nAction: Delegate work to coworker\nAction Input: {\n \"coworker\":
\"Scorer\", \n \"task\": \"Provide an integer score between 1-5 for the following
title: ''The impact of AI in the future of work''\",\n \"context\": \"The
score should reflect how compelling and relevant the title is regarding the
integration and impact of Artificial Intelligence on future work scenarios.\"\n}\nObservation:
4"}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3198'
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-A81lAXZSR28oNpAYfswuPOsPNrgwT\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476752,\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.\\n\\nFinal
Answer: 4\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
699,\n \"completion_tokens\": 14,\n \"total_tokens\": 713,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f9ef61b6a2233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:52:32 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:
- '289'
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:
- '29999235'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_846b3a2ab18919d9a8657caeccaf99b1
http_version: HTTP/1.1
status_code: 200
version: 1