mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-19 21:08:13 +00:00
removing langchain
This commit is contained in:
João Moura
804
tests/cassettes/test_increment_tool_errors.yaml
Normal file
804
tests/cassettes/test_increment_tool_errors.yaml
Normal file
@@ -0,0 +1,804 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: !!binary |
|
||||
Cv0KCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS1AoKEgoQY3Jld2FpLnRl
|
||||
bGVtZXRyeRKcAQoQGpWU7gV7gyM1X5tKq1MGOhIIcli7XULaxP4qClRvb2wgVXNhZ2UwATkwsAl9
|
||||
U3D0F0FIlA19U3D0F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjU1LjJKKAoJdG9vbF9uYW1lEhsK
|
||||
GURlbGVnYXRlIHdvcmsgdG8gY293b3JrZXJKDgoIYXR0ZW1wdHMSAhgBegIYAYUBAAEAABKQAgoQ
|
||||
h3LGEzc6sqEX2iWRA1A1GRIIr0vmwYXNK6kqDlRhc2sgRXhlY3V0aW9uMAE5gCrjjlJw9BdBOFZq
|
||||
vlNw9BdKLgoIY3Jld19rZXkSIgogNzQyNzU3MzEyZWY3YmI0ZWUwYjA2NjJkMWMyZTIxNzlKMQoH
|
||||
Y3Jld19pZBImCiRhODQ2M2Y1My1iZGJiLTQxYjMtYTQzNC03MmQzN2JiN2Y3NjNKLgoIdGFza19r
|
||||
ZXkSIgogMjdlZjM4Y2M5OWRhNGE4ZGVkNzBlZDQwNmU0NGFiODZKMQoHdGFza19pZBImCiRiMTUz
|
||||
MzA4Yy1hNjk0LTRhZjAtYTY2ZC0yOGRmNGE3MzcwYTN6AhgBhQEAAQAAEosHChD7d622aCh3C4Kw
|
||||
h7CCLF+jEgiChWUPzaPdAyoMQ3JldyBDcmVhdGVkMAE5QJQIwVNw9BdB6GYLwVNw9BdKGgoOY3Jl
|
||||
d2FpX3ZlcnNpb24SCAoGMC41NS4yShoKDnB5dGhvbl92ZXJzaW9uEggKBjMuMTEuN0ouCghjcmV3
|
||||
X2tleRIiCiAzMDNiOGVkZDViMDA4NzEwZDc2YWFmODI1YTcwOWU1NUoxCgdjcmV3X2lkEiYKJDdl
|
||||
MGFjZDcxLTliOTUtNGViMS05NDExLTA0NDFhODFkNmVmM0oeCgxjcmV3X3Byb2Nlc3MSDgoMaGll
|
||||
cmFyY2hpY2FsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFK
|
||||
GwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUrbAgoLY3Jld19hZ2VudHMSywIKyAJbeyJrZXki
|
||||
OiAiOTJlN2ViMTkxNjY0YzkzNTc4NWVkN2Q0MjQwYTI5NGQiLCAiaWQiOiAiMTY2YmVmNTMtMDM5
|
||||
Yi00MDhhLTk0MTEtYjJiZDE3NDhhMWFiIiwgInJvbGUiOiAiU2NvcmVyIiwgInZlcmJvc2U/Ijog
|
||||
ZmFsc2UsICJtYXhfaXRlciI6IDI1LCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5n
|
||||
X2xsbSI6IG51bGwsICJsbG0iOiAiZ3B0LTRvIiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiB0cnVl
|
||||
LCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAi
|
||||
dG9vbHNfbmFtZXMiOiBbInNjb3JpbmdfZXhhbXBsZXMiXX1dStsBCgpjcmV3X3Rhc2tzEswBCskB
|
||||
W3sia2V5IjogImYzNTc1YjAxM2MyMjk0YjdjYzhlODAzMTU1YzhiYTQ2IiwgImlkIjogImJmMjcz
|
||||
NzNlLTA0M2YtNDk3My1hMDM2LWZiNzE4OTEyOTIwYiIsICJhc3luY19leGVjdXRpb24/IjogZmFs
|
||||
c2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiTm9uZSIsICJhZ2VudF9r
|
||||
ZXkiOiBudWxsLCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAAA==
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '1408'
|
||||
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:
|
||||
- Thu, 12 Sep 2024 08:01:06 GMT
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
- 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'', check examples to based your evaluation.\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-4-0125-preview", "stop":
|
||||
["\nObservation"]}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '3034'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
|
||||
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
|
||||
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-A6Z38ir9Vhym04xT66OQrDky4EI34\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1726128062,\n \"model\": \"gpt-4-0125-preview\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"Thought: Before assigning a score, I
|
||||
must understand the criteria that we use for evaluation. Since I cannot evaluate
|
||||
the title myself, I need to delegate the task to my coworker, Scorer, providing
|
||||
them with all the necessary context to assess the title appropriately.\\n\\nAction:
|
||||
Delegate work to coworker\\nAction Input: {\\\"task\\\": \\\"Evaluate title\\\",
|
||||
\\\"context\\\": \\\"We need to give an integer score between 1-5 for the title:
|
||||
'The impact of AI in the future of work'. The score should be based on relevance,
|
||||
insightfulness, and originality. Please consider these criteria when evaluating
|
||||
the title.\\\", \\\"coworker\\\": \\\"Scorer\\\"}\",\n \"refusal\": null\n
|
||||
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
|
||||
\ ],\n \"usage\": {\n \"prompt_tokens\": 672,\n \"completion_tokens\":
|
||||
135,\n \"total_tokens\": 807\n },\n \"system_fingerprint\": null\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 8c1e5e06bbdc6280-GRU
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Thu, 12 Sep 2024 08:01:08 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:
|
||||
- '5366'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=15552000; includeSubDomains; preload
|
||||
x-ratelimit-limit-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '2000000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '1999259'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 22ms
|
||||
x-request-id:
|
||||
- req_0256635e5f90bc1005c9c2897c1899e4
|
||||
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\nYou
|
||||
ONLY have access to the following tools, and should NEVER make up tools that
|
||||
are not listed here:\n\nTool Name: scoring_examples(*args: Any, **kwargs: Any)
|
||||
-> Any\nTool Description: scoring_examples() - Useful examples for scoring titles.
|
||||
\nTool Arguments: {}\n\nUse the following format:\n\nThought: you should always
|
||||
think about what to do\nAction: the action to take, only one name of [scoring_examples],
|
||||
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: Evaluate title\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 give an integer score between 1-5 for the
|
||||
title: ''The impact of AI in the future of work''. The score should be based
|
||||
on relevance, insightfulness, and originality. Please consider these criteria
|
||||
when evaluating the title.\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:
|
||||
- '1646'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
|
||||
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
|
||||
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-A6Z3EMuWJ0zfPW7ZBkzpCDZA7UghH\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1726128068,\n \"model\": \"gpt-4o-2024-05-13\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"To accurately score the title 'The impact
|
||||
of AI in the future of work' based on relevance, insightfulness, and originality,
|
||||
I should first gather some useful examples for scoring titles.\\n\\nAction:
|
||||
scoring_examples\\nAction Input: {}\",\n \"refusal\": null\n },\n
|
||||
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
|
||||
\ \"usage\": {\n \"prompt_tokens\": 329,\n \"completion_tokens\": 46,\n
|
||||
\ \"total_tokens\": 375\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 8c1e5e2af9fc6280-GRU
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Thu, 12 Sep 2024 08:01:09 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:
|
||||
- '962'
|
||||
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:
|
||||
- '29999602'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 0s
|
||||
x-request-id:
|
||||
- req_f5d3635348e20fcfa7f86ee64ec68072
|
||||
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\nYou
|
||||
ONLY have access to the following tools, and should NEVER make up tools that
|
||||
are not listed here:\n\nTool Name: scoring_examples(*args: Any, **kwargs: Any)
|
||||
-> Any\nTool Description: scoring_examples() - Useful examples for scoring titles.
|
||||
\nTool Arguments: {}\n\nUse the following format:\n\nThought: you should always
|
||||
think about what to do\nAction: the action to take, only one name of [scoring_examples],
|
||||
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: Evaluate title\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 give an integer score between 1-5 for the
|
||||
title: ''The impact of AI in the future of work''. The score should be based
|
||||
on relevance, insightfulness, and originality. Please consider these criteria
|
||||
when evaluating the title.\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 accurately score the title ''The impact
|
||||
of AI in the future of work'' based on relevance, insightfulness, and originality,
|
||||
I should first gather some useful examples for scoring titles.\n\nAction: scoring_examples\nAction
|
||||
Input: {}\nObservation: \nI encountered an error while trying to use the tool.
|
||||
This was the error: Error.\n Tool scoring_examples accepts these inputs: scoring_examples()
|
||||
- Useful examples for scoring titles. .\nMoving on then. I MUST either use a
|
||||
tool (use one at time) OR give my best final answer. To Use the following format:\n\nThought:
|
||||
you should always think about what to do\nAction: the action to take, should
|
||||
be one of [scoring_examples]\nAction Input: the input to the action, dictionary
|
||||
enclosed in curly braces\nObservation: the result of the action\n... (this Thought/Action/Action
|
||||
Input/Observation can repeat N times)\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\n "}], "model": "gpt-4o", "stop": ["\nObservation"]}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '2700'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
|
||||
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
|
||||
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-A6Z3FGyPXjQLqtQi1bP839f3sXJTR\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1726128069,\n \"model\": \"gpt-4o-2024-05-13\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"I will make another attempt to gather
|
||||
useful examples for scoring titles to ensure my evaluation is accurate.\\n\\nAction:
|
||||
scoring_examples\\nAction Input: {}\",\n \"refusal\": null\n },\n
|
||||
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
|
||||
\ \"usage\": {\n \"prompt_tokens\": 547,\n \"completion_tokens\": 28,\n
|
||||
\ \"total_tokens\": 575\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 8c1e5e33be1c6280-GRU
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Thu, 12 Sep 2024 08:01:10 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:
|
||||
- '522'
|
||||
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:
|
||||
- '29999351'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 1ms
|
||||
x-request-id:
|
||||
- req_ca6ab2c18724eab9c3cf14e0420b62a6
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
- request:
|
||||
body: !!binary |
|
||||
CqYBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSfgoSChBjcmV3YWkudGVs
|
||||
ZW1ldHJ5EmgKELy5u7S9ciySMmk+s0SGxW4SCE4a9Lw+zbFYKhBUb29sIFVzYWdlIEVycm9yMAE5
|
||||
+D9Fb1Vw9BdBcA5Kb1Vw9BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC41NS4yegIYAYUBAAEAAA==
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '169'
|
||||
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:
|
||||
- Thu, 12 Sep 2024 08:01:11 GMT
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
- 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\nYou
|
||||
ONLY have access to the following tools, and should NEVER make up tools that
|
||||
are not listed here:\n\nTool Name: scoring_examples(*args: Any, **kwargs: Any)
|
||||
-> Any\nTool Description: scoring_examples() - Useful examples for scoring titles.
|
||||
\nTool Arguments: {}\n\nUse the following format:\n\nThought: you should always
|
||||
think about what to do\nAction: the action to take, only one name of [scoring_examples],
|
||||
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: Evaluate title\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 give an integer score between 1-5 for the
|
||||
title: ''The impact of AI in the future of work''. The score should be based
|
||||
on relevance, insightfulness, and originality. Please consider these criteria
|
||||
when evaluating the title.\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 accurately score the title ''The impact
|
||||
of AI in the future of work'' based on relevance, insightfulness, and originality,
|
||||
I should first gather some useful examples for scoring titles.\n\nAction: scoring_examples\nAction
|
||||
Input: {}\nObservation: \nI encountered an error while trying to use the tool.
|
||||
This was the error: Error.\n Tool scoring_examples accepts these inputs: scoring_examples()
|
||||
- Useful examples for scoring titles. .\nMoving on then. I MUST either use a
|
||||
tool (use one at time) OR give my best final answer. To Use the following format:\n\nThought:
|
||||
you should always think about what to do\nAction: the action to take, should
|
||||
be one of [scoring_examples]\nAction Input: the input to the action, dictionary
|
||||
enclosed in curly braces\nObservation: the result of the action\n... (this Thought/Action/Action
|
||||
Input/Observation can repeat N times)\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\n "}, {"role": "assistant", "content": "I will
|
||||
make another attempt to gather useful examples for scoring titles to ensure
|
||||
my evaluation is accurate.\n\nAction: scoring_examples\nAction Input: {}\nObservation:
|
||||
\nI encountered an error while trying to use the tool. This was the error: Error.\n
|
||||
Tool scoring_examples accepts these inputs: scoring_examples() - Useful examples
|
||||
for scoring titles. .\nMoving on then. I MUST either use a tool (use one at
|
||||
time) OR give my best final answer. To Use the following format:\n\nThought:
|
||||
you should always think about what to do\nAction: the action to take, should
|
||||
be one of [scoring_examples]\nAction Input: the input to the action, dictionary
|
||||
enclosed in curly braces\nObservation: the result of the action\n... (this Thought/Action/Action
|
||||
Input/Observation can repeat N times)\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\n "}], "model": "gpt-4o", "stop": ["\nObservation"]}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '3677'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
|
||||
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
|
||||
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-A6Z3GzC7QdzdIS35KeUPkd98Pok9p\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1726128070,\n \"model\": \"gpt-4o-2024-05-13\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"Given the persistent issue with retrieving
|
||||
examples, I will leverage my expertise to evaluate the title based on the criteria
|
||||
provided: relevance, insightfulness, and originality.\\n\\nThought: I will evaluate
|
||||
the title 'The impact of AI in the future of work' using the three criteria
|
||||
directly.\\n\\n1. **Relevance:** \\n - The title is highly relevant as AI
|
||||
is a significant and timely topic in today's technological landscape.\\n -
|
||||
The future of work is a pertinent issue affecting a broad audience, including
|
||||
industries, employees, and policymakers.\\n\\n2. **Insightfulness:**\\n -
|
||||
The title promises an examination of AI's impact, which suggests an exploration
|
||||
of both potential benefits and challenges.\\n - It invites a discussion on
|
||||
how AI could reshape the workforce, hinting at valuable insights for preparing
|
||||
for future changes.\\n\\n3. **Originality:**\\n - The concept of AI influencing
|
||||
the future of work is a common discussion point in many academic and industry
|
||||
circles.\\n - However, the title doesn't hint at a unique angle or novel perspective
|
||||
that sets it apart from other similar works.\\n\\nBased on these points, I will
|
||||
score the title accordingly.\\n\\nFinal Answer: Based on relevance (5), insightfulness
|
||||
(4), and originality (3):\\n\\n**Final Score: 4**\",\n \"refusal\": null\n
|
||||
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
|
||||
\ ],\n \"usage\": {\n \"prompt_tokens\": 747,\n \"completion_tokens\":
|
||||
252,\n \"total_tokens\": 999\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 8c1e5e39d87d6280-GRU
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Thu, 12 Sep 2024 08:01:14 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:
|
||||
- '3391'
|
||||
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:
|
||||
- '29999119'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 1ms
|
||||
x-request-id:
|
||||
- req_198e30d47bf1cfd5979af826a36e4c58
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
- request:
|
||||
body: !!binary |
|
||||
CsYCCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSnQIKEgoQY3Jld2FpLnRl
|
||||
bGVtZXRyeRJoChCMo9WDZAlYK58kAM8/CEQsEgjOTYPwOZ0v6CoQVG9vbCBVc2FnZSBFcnJvcjAB
|
||||
OSDEO6lVcPQXQRD8QKlVcPQXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuNTUuMnoCGAGFAQABAAAS
|
||||
nAEKECjsvAFKsK4VP6bGPZdG/RISCHc4LY7teq30KgpUb29sIFVzYWdlMAE5IBQMjVZw9BdBCIMP
|
||||
jVZw9BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC41NS4ySigKCXRvb2xfbmFtZRIbChlEZWxlZ2F0
|
||||
ZSB3b3JrIHRvIGNvd29ya2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAA=
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '329'
|
||||
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:
|
||||
- Thu, 12 Sep 2024 08:01:16 GMT
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
- 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'', check examples to based your evaluation.\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": "Thought:
|
||||
Before assigning a score, I must understand the criteria that we use for evaluation.
|
||||
Since I cannot evaluate the title myself, I need to delegate the task to my
|
||||
coworker, Scorer, providing them with all the necessary context to assess the
|
||||
title appropriately.\n\nAction: Delegate work to coworker\nAction Input: {\"task\":
|
||||
\"Evaluate title\", \"context\": \"We need to give an integer score between
|
||||
1-5 for the title: ''The impact of AI in the future of work''. The score should
|
||||
be based on relevance, insightfulness, and originality. Please consider these
|
||||
criteria when evaluating the title.\", \"coworker\": \"Scorer\"}\nObservation:
|
||||
Based on relevance (5), insightfulness (4), and originality (3):\n\n**Final
|
||||
Score: 4**"}], "model": "gpt-4-0125-preview", "stop": ["\nObservation"]}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '3801'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
|
||||
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
|
||||
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-A6Z3KZMtHCI3KHSZ8UIt3DAfN3ONf\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1726128074,\n \"model\": \"gpt-4-0125-preview\",\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\":
|
||||
838,\n \"completion_tokens\": 14,\n \"total_tokens\": 852\n },\n \"system_fingerprint\":
|
||||
null\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 8c1e5e51b9be6280-GRU
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Thu, 12 Sep 2024 08:01:18 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:
|
||||
- '3884'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=15552000; includeSubDomains; preload
|
||||
x-ratelimit-limit-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '2000000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '1999080'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 27ms
|
||||
x-request-id:
|
||||
- req_4388c534a4e3cc95495ce98010ad7001
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
version: 1
|
||||
Reference in New Issue
Block a user