andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-10 16:48:30 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity
Files
e5ff0363d923a6de9d7d529e02f3a4ba40624213
crewAI/tests/cassettes/test_increment_tool_errors.yaml
João Moura e5ff0363d9 final pass
2024-09-16 06:16:48 -03:00

1048 lines
52 KiB
YAML
Raw Blame History

interactions:
- request:
body: !!binary |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=
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1250'
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 08:52:37 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'', check examples to based your evaluation.\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-4-0125-preview",
"stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3068'
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-A81lBF0zaA4TP9ttqpGSfH4uvOh52\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476753,\n \"model\": \"gpt-4-0125-preview\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: To accurately score the title
\\\"The impact of AI in the future of work\\\" based on the provided criteria
and examples, I need to understand what specific attributes or factors should
be considered for the evaluation. Since I don't have immediate access to the
examples or any pre-defined criteria, it would be beneficial to clarify what
elements make a title score higher or lower within the 1-5 range. Is it the
clarity of the title, the relevance to current trends, the potential for engaging
discussion, or another factor altogether? Once I understand these criteria,
I can more effectively evaluate the title.\\n\\nAction: Ask question to coworker\\n\\nAction
Input: {\\\"question\\\": \\\"What specific criteria or factors should be considered
when scoring the title 'The impact of AI in the future of work' between 1-5?
Are we looking at clarity, relevance, potential for engaging discussion, or
any other specific attributes?\\\", \\\"context\\\": \\\"The task is to provide
an integer score between 1-5 for the mentioned title, based on examples and
criteria for evaluation. However, the examples and criteria have not been provided,
making it essential to understand what attributes or factors are crucial for
this evaluation.\\\", \\\"coworker\\\": \\\"Scorer\\\"}\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 676,\n \"completion_tokens\":
248,\n \"total_tokens\": 924,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f9ef9dc9c2233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:52:39 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:
- '6679'
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_8245019a3da6701f9b671febd97f8a8c
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\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"}, {"role": "user", "content": "\nCurrent Task: What specific criteria
or factors should be considered when scoring the title ''The impact of AI in
the future of work'' between 1-5? Are we looking at clarity, relevance, potential
for engaging discussion, or any other specific attributes?\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 task is to provide an integer score between 1-5 for the mentioned
title, based on examples and criteria for evaluation. However, the examples
and criteria have not been provided, making it essential to understand what
attributes or factors are crucial for this evaluation.\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:
- '1948'
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-A81lIQToUkwKyVfplL8CFSKbnE9l3\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476760,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to understand the specific
criteria or factors that are considered important when scoring titles. This
will help me accurately evaluate \\\"The impact of AI in the future of work\\\"
on a scale from 1 to 5.\\n\\nAction: scoring_examples\\nAction Input: {}\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 380,\n \"completion_tokens\":
55,\n \"total_tokens\": 435,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f9f2578ca2233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:52:40 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:
- '632'
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:
- '29999535'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_c69c025f2e32e70c389a19c58e26b008
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\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"}, {"role": "user", "content": "\nCurrent Task: What specific criteria
or factors should be considered when scoring the title ''The impact of AI in
the future of work'' between 1-5? Are we looking at clarity, relevance, potential
for engaging discussion, or any other specific attributes?\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 task is to provide an integer score between 1-5 for the mentioned
title, based on examples and criteria for evaluation. However, the examples
and criteria have not been provided, making it essential to understand what
attributes or factors are crucial for this evaluation.\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 understand the specific criteria or factors that are considered important
when scoring titles. This will help me accurately evaluate \"The impact of AI
in the future of work\" on a scale from 1 to 5.\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 not both at the same time.
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/Result 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:
- '3055'
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-A81lI9SpIOcixWcMY0sLZ725032T7\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476760,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I should attempt to use the
scoring_examples tool again since I need examples to understand the criteria
for evaluating 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\": 613,\n \"completion_tokens\":
33,\n \"total_tokens\": 646,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f9f2b4a3f2233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:52:41 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:
- '464'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15552000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999270'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_447b7dfb2046e9bcc3152694f9fc28d5
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\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"}, {"role": "user", "content": "\nCurrent Task: What specific criteria
or factors should be considered when scoring the title ''The impact of AI in
the future of work'' between 1-5? Are we looking at clarity, relevance, potential
for engaging discussion, or any other specific attributes?\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 task is to provide an integer score between 1-5 for the mentioned
title, based on examples and criteria for evaluation. However, the examples
and criteria have not been provided, making it essential to understand what
attributes or factors are crucial for this evaluation.\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 understand the specific criteria or factors that are considered important
when scoring titles. This will help me accurately evaluate \"The impact of AI
in the future of work\" on a scale from 1 to 5.\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 not both at the same time.
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/Result 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": "Thought: I should attempt to use the scoring_examples
tool again since I need examples to understand the criteria for evaluating 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
not both at the same time. 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/Result 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:
- '4080'
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-A81lJPd5FLU2fjPQws6gn4D0uShfu\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476761,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I should attempt to use the
scoring_examples tool again to obtain the examples needed for scoring titles.
This time, I'll ensure that the input is formatted correctly to avoid any issues.\\n\\nAction:
scoring_examples\\nAction Input: {}\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 824,\n \"completion_tokens\": 46,\n
\ \"total_tokens\": 870,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f9f300be32233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:52:42 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:
- '503'
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:
- '29999028'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_e7fbab1a3e9f3a1f9b6566d7cccc2dbe
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
CpECCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS6AEKEgoQY3Jld2FpLnRl
bGVtZXRyeRJoChAUEIOphW2OYs9t6CiWoXmGEgioWipNgxPpuyoQVG9vbCBVc2FnZSBFcnJvcjAB
Ofj58Wt3rfUXQYCtAWx3rfUXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuNTYuM3oCGAGFAQABAAAS
aAoQ1g7OL9J8Xt6TjSndzRIEShII3bYt+8dxQOYqEFRvb2wgVXNhZ2UgRXJyb3IwATmIzgqZd631
F0Ewmw6Zd631F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjU2LjN6AhgBhQEAAQAA
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '276'
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 08:52:42 GMT
status:
code: 200
message: OK
- 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\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"}, {"role": "user", "content": "\nCurrent Task: What specific criteria
or factors should be considered when scoring the title ''The impact of AI in
the future of work'' between 1-5? Are we looking at clarity, relevance, potential
for engaging discussion, or any other specific attributes?\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 task is to provide an integer score between 1-5 for the mentioned
title, based on examples and criteria for evaluation. However, the examples
and criteria have not been provided, making it essential to understand what
attributes or factors are crucial for this evaluation.\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 understand the specific criteria or factors that are considered important
when scoring titles. This will help me accurately evaluate \"The impact of AI
in the future of work\" on a scale from 1 to 5.\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 not both at the same time.
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/Result 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": "Thought: I should attempt to use the scoring_examples
tool again since I need examples to understand the criteria for evaluating 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
not both at the same time. 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/Result 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": "Thought:
I should attempt to use the scoring_examples tool again to obtain the examples
needed for scoring titles. This time, I''ll ensure that the input is formatted
correctly to avoid any issues.\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 not both at the same time. 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/Result 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:
- '5165'
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-A81lKEy11PpkVyLGltSBhEfz4JSZt\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476762,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: Since I am unable to get examples
from the tool, I will have to proceed by giving the best answer based on logical
reasoning and commonly accepted criteria for evaluating titles.\\n\\nFinal Answer:
When scoring the title \\\"The impact of AI in the future of work\\\" between
1-5, the following specific criteria or factors should be considered:\\n\\n1.
**Clarity**: The title should clearly convey the topic and scope of the content.
It should be easy to understand and leave no ambiguity about the subject matter.\\n2.
**Relevance**: The title should be relevant to current trends, issues, and discussions
in the field of Artificial Intelligence and the future of work. It should address
a significant and timely topic.\\n3. **Specificity**: The title should be specific
enough to give a clear indication of what aspects of AI and the future of work
will be explored, but broad enough to allow for a comprehensive discussion.\\n4.
**Engagement Potential**: The title should be engaging and intriguing, sparking
curiosity and interest in the audience. It should encourage readers to want
to learn more about the topic.\\n5. **Scope for Discussion**: The title should
have the potential to foster a meaningful and in-depth discussion. It should
open up avenues for exploring various impacts, challenges, and opportunities
related to AI in the future workplace.\\n\\nA score of 1 would indicate that
the title fails to meet these criteria, while a score of 5 would indicate that
the title excels in all these areas.\\n\\nGiven these criteria, here is an example
evaluation of \\\"The impact of AI in the future of work\\\":\\n\\n- **Clarity**:
The title is clear and straightforward. (Score: 5)\\n- **Relevance**: The topic
is highly relevant to current technological and societal trends. (Score: 5)\\n-
**Specificity**: The title could be a bit more specific, perhaps by narrowing
down what aspects of AI or which sectors of work will be impacted. (Score: 4)\\n-
**Engagement Potential**: The title is engaging, as it addresses a significant
and intriguing topic. (Score: 5)\\n- **Scope for Discussion**: The title opens
up a broad range of potential discussion points. (Score: 5)\\n\\nAverage Score:
(5+5+4+5+5)/5 = 4.8\\n\\nTherefore, \\\"The impact of AI in the future of work\\\"
would likely receive a high score, close to 5, when evaluated using these criteria.\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 1048,\n \"completion_tokens\":
509,\n \"total_tokens\": 1557,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f9f350d962233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:52:47 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:
- '4695'
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:
- '29998769'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_39ca8adb0689c76fb8166ebf8f70cc8e
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
CqYBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSfgoSChBjcmV3YWkudGVs
ZW1ldHJ5EmgKEC2f4EvH1JAo9lxrfRcZXt4SCFwK6ZggQ9/hKhBUb29sIFVzYWdlIEVycm9yMAE5
YJeUyHet9RdB8FuayHet9RdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC41Ni4zegIYAYUBAAEAAA==
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:
- Mon, 16 Sep 2024 08:52:47 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'', check examples to based your evaluation.\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":
"Thought: To accurately score the title \"The impact of AI in the future of
work\" based on the provided criteria and examples, I need to understand what
specific attributes or factors should be considered for the evaluation. Since
I don''t have immediate access to the examples or any pre-defined criteria,
it would be beneficial to clarify what elements make a title score higher or
lower within the 1-5 range. Is it the clarity of the title, the relevance to
current trends, the potential for engaging discussion, or another factor altogether?
Once I understand these criteria, I can more effectively evaluate the title.\n\nAction:
Ask question to coworker\n\nAction Input: {\"question\": \"What specific criteria
or factors should be considered when scoring the title ''The impact of AI in
the future of work'' between 1-5? Are we looking at clarity, relevance, potential
for engaging discussion, or any other specific attributes?\", \"context\": \"The
task is to provide an integer score between 1-5 for the mentioned title, based
on examples and criteria for evaluation. However, the examples and criteria
have not been provided, making it essential to understand what attributes or
factors are crucial for this evaluation.\", \"coworker\": \"Scorer\"}\nObservation:
When scoring the title \"The impact of AI in the future of work\" between 1-5,
the following specific criteria or factors should be considered:\n\n1. **Clarity**:
The title should clearly convey the topic and scope of the content. It should
be easy to understand and leave no ambiguity about the subject matter.\n2. **Relevance**:
The title should be relevant to current trends, issues, and discussions in the
field of Artificial Intelligence and the future of work. It should address a
significant and timely topic.\n3. **Specificity**: The title should be specific
enough to give a clear indication of what aspects of AI and the future of work
will be explored, but broad enough to allow for a comprehensive discussion.\n4.
**Engagement Potential**: The title should be engaging and intriguing, sparking
curiosity and interest in the audience. It should encourage readers to want
to learn more about the topic.\n5. **Scope for Discussion**: The title should
have the potential to foster a meaningful and in-depth discussion. It should
open up avenues for exploring various impacts, challenges, and opportunities
related to AI in the future workplace.\n\nA score of 1 would indicate that the
title fails to meet these criteria, while a score of 5 would indicate that the
title excels in all these areas.\n\nGiven these criteria, here is an example
evaluation of \"The impact of AI in the future of work\":\n\n- **Clarity**:
The title is clear and straightforward. (Score: 5)\n- **Relevance**: The topic
is highly relevant to current technological and societal trends. (Score: 5)\n-
**Specificity**: The title could be a bit more specific, perhaps by narrowing
down what aspects of AI or which sectors of work will be impacted. (Score: 4)\n-
**Engagement Potential**: The title is engaging, as it addresses a significant
and intriguing topic. (Score: 5)\n- **Scope for Discussion**: The title opens
up a broad range of potential discussion points. (Score: 5)\n\nAverage Score:
(5+5+4+5+5)/5 = 4.8\n\nTherefore, \"The impact of AI in the future of work\"
would likely receive a high score, close to 5, when evaluated using these criteria."}],
"model": "gpt-4-0125-preview", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '6512'
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-A81lPXGHQidXo4yJaPzDZVihVwbVB\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476767,\n \"model\": \"gpt-4-0125-preview\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: Based on the criteria outlined
by the response from Scorer, it seems clear now how to evaluate the title \\\"The
impact of AI in the future of work\\\". The criteria of clarity, relevance,
specificity, engagement potential, and scope for discussion will guide the scoring
process. The details provided indicate that the title does very well in most
areas, with slight room for improvement in specificity according to the given
evaluation. However, since the scoring must be an integer between 1 and 5, and
given the example evaluation breakdown, the final average suggests that the
title should be closely rounded or considered against the highest possible score,
which is 5, taking into account how it excels in most criteria with a minor
consideration for improvement in specificity.\\n\\nFinal Answer: The score of
the title \\\"The impact of AI in the future of work\\\" is 5.\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 1392,\n \"completion_tokens\":
172,\n \"total_tokens\": 1564,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f9f542fbf2233-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:52:52 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:
- '4929'
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:
- '1998417'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 47ms
x-request-id:
- req_7117672fbbb3038bfca668109915fdb9
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink