andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-08 23:58:34 +00:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity
Files
539b910d7d173c73e326f0f0ba9ce3cd5317f0a7
crewAI/tests/cassettes/test_cache_hitting_between_agents.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

576 lines
26 KiB
YAML
Raw Blame History

interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
time CEO of a content creation agency with a Senior Writer on the team. You''re
now working on a new project and want to make sure the content produced is amazing.\nYour
personal goal is: Make sure the writers in your company produce amazing content.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: multiplier(*args: Any, **kwargs: Any) ->
Any\nTool Description: multiplier(first_number: ''integer'', second_number:
''integer'') - Useful for when you need to multiply two numbers together. \nTool
Arguments: {''first_number'': {''title'': ''First Number'', ''type'': ''integer''},
''second_number'': {''title'': ''Second Number'', ''type'': ''integer''}}\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: Researcher\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: Researcher\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 [multiplier, 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: What is 2 tims 6? Return only the number.\n\nThis is the expect
criteria for your final answer: the result of multiplication\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:
- '3110'
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-A81hCiq9qgl0YS5UWruPw3OqLmue1\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476506,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: To find the result of multiplying
2 by 6, I will use the multiplier tool.\\n\\nAction: multiplier\\nAction Input:
{\\\"first_number\\\": 2, \\\"second_number\\\": 6}\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 691,\n \"completion_tokens\":
42,\n \"total_tokens\": 733,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f98f60d6d2233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:48:27 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:
- '539'
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:
- '29999244'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_3a4c713c93208ea7f9a903d72682efb3
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:
- '2104'
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 08:48:27 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
time CEO of a content creation agency with a Senior Writer on the team. You''re
now working on a new project and want to make sure the content produced is amazing.\nYour
personal goal is: Make sure the writers in your company produce amazing content.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: multiplier(*args: Any, **kwargs: Any) ->
Any\nTool Description: multiplier(first_number: ''integer'', second_number:
''integer'') - Useful for when you need to multiply two numbers together. \nTool
Arguments: {''first_number'': {''title'': ''First Number'', ''type'': ''integer''},
''second_number'': {''title'': ''Second Number'', ''type'': ''integer''}}\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: Researcher\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: Researcher\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 [multiplier, 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: What is 2 tims 6? Return only the number.\n\nThis is the expect
criteria for your final answer: the result of multiplication\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": "Thought:
To find the result of multiplying 2 by 6, I will use the multiplier tool.\n\nAction:
multiplier\nAction Input: {\"first_number\": 2, \"second_number\": 6}\nObservation:
12"}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3328'
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-A81hDHCkswF9m2kBlGAiHP6IpNArZ\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476507,\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: 12\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
741,\n \"completion_tokens\": 14,\n \"total_tokens\": 755,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f98fb3eef2233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:48:27 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:
- '284'
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:
- '29999201'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_bd80ed5919e329e00f16896680ba9f0f
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
an expert researcher, specialized in technology, software engineering, AI and
startups. You work as a freelancer and is now working on doing research and
analysis for a new customer.\nYour personal goal is: Make the best research
and analysis on content about AI and AI agents\nYou ONLY have access to the
following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: multiplier(*args: Any, **kwargs: Any) -> Any\nTool Description: multiplier(first_number:
''integer'', second_number: ''integer'') - Useful for when you need to multiply
two numbers together. \nTool Arguments: {''first_number'': {''title'': ''First
Number'', ''type'': ''integer''}, ''second_number'': {''title'': ''Second Number'',
''type'': ''integer''}}\n\nUse the following format:\n\nThought: you should
always think about what to do\nAction: the action to take, only one name of
[multiplier], 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: What is 2 times 6? Return only the number.\n\nThis
is the expect criteria for your final answer: the result of multiplication\nyou
MUST return the actual complete content as the final answer, not a summary.\n\nThis
is the context you''re working with:\n12\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:
- '1791'
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-A81hEHvna5Boh4CvINffrtWAuMJNc\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476508,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to multiply 2 by 6 to
find the answer.\\n\\nAction: multiplier\\nAction Input: {\\\"first_number\\\":
2, \\\"second_number\\\": 6}\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
365,\n \"completion_tokens\": 37,\n \"total_tokens\": 402,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f98fecfed2233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:48:29 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:
- '1056'
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:
- '29999573'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_6da9ff4632c3a536c7a2c54177ef2b61
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
an expert researcher, specialized in technology, software engineering, AI and
startups. You work as a freelancer and is now working on doing research and
analysis for a new customer.\nYour personal goal is: Make the best research
and analysis on content about AI and AI agents\nYou ONLY have access to the
following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: multiplier(*args: Any, **kwargs: Any) -> Any\nTool Description: multiplier(first_number:
''integer'', second_number: ''integer'') - Useful for when you need to multiply
two numbers together. \nTool Arguments: {''first_number'': {''title'': ''First
Number'', ''type'': ''integer''}, ''second_number'': {''title'': ''Second Number'',
''type'': ''integer''}}\n\nUse the following format:\n\nThought: you should
always think about what to do\nAction: the action to take, only one name of
[multiplier], 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: What is 2 times 6? Return only the number.\n\nThis
is the expect criteria for your final answer: the result of multiplication\nyou
MUST return the actual complete content as the final answer, not a summary.\n\nThis
is the context you''re working with:\n12\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": "Thought: I need to multiply
2 by 6 to find the answer.\n\nAction: multiplier\nAction Input: {\"first_number\":
2, \"second_number\": 6}\nObservation: 12"}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1981'
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-A81hF2H3ytkFpG5x87L5fnUzhaElJ\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476509,\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: 12\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
410,\n \"completion_tokens\": 14,\n \"total_tokens\": 424,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f99073aac2233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:48:29 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:
- '257'
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:
- '29999536'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_09f9c36777b5e83670f0e116f0de6c50
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink