andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-12 01:28:30 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity
Files
8ca08217189345b0d28ce7174bee700faea5bdcf
crewAI/tests/cassettes/test_increment_tool_errors.yaml
João Moura 8ca0821718 making sure all tests pass
2024-09-15 19:37:58 -03:00

1096 lines
56 KiB
YAML
Raw Blame History

interactions:
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1409'
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:
- Sun, 15 Sep 2024 22:13:40 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=xCQEG8vgEvQfut0bkj2xgre9z9ePZhdKdNxBphhvH6s-1726437753-1.0.1.1-5qo0zwDCcKDtqvIzDbp2sLEPCey8v5DAsf0Mg6f2RmooOW9FXTw2P66VCTTF.vCwTpWBIFk0vzKmBAPOt6urIg;
_cfuvid=TiTyEciy7HrUlIDEsELZqkUyM4Fyn8OldZd4JefFMOA-1726437753108-0.0.1.1-604800000
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-A7rmrleUP0T3H0IOUHqJips8kcmxI\",\n \"object\":
\"chat.completion\",\n \"created\": 1726438417,\n \"model\": \"gpt-4-0125-preview\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: To accurately evaluate the given
title 'The impact of AI in the future of work' against the specified criteria
(an integer score between 1-5), I need to understand the criteria that my coworker,
Scorer, will use for assessment. This involves knowing what makes a title score
a 1 versus a 5 and any gradations in between. I should gather all available
context regarding this scoring system before delegating the task of scoring
the title to Scorer. It's important to make sure the evaluation criteria are
clear to ensure the scoring process aligns with the expectations.\\n\\nAction:
Ask question to coworker\\n\\nAction Input: {\\\"question\\\": \\\"Can you explain
the criteria used to assign a score between 1-5 to a title? Specifically, I'm
interested in understanding what aspects or qualities of a title would make
it score at each level of this scale. The task at hand involves scoring the
title 'The impact of AI in the future of work', so examples relevant to technology
or future-oriented themes would be especially helpful.\\\", \\\"context\\\":
\\\"A score needs to be assigned to the title 'The impact of AI in the future
of work', based on its relevance, impact, originality, and clarity. The scoring
system ranges from 1 to 5, but the precise criteria for what constitutes each
score level hasn't been specified. Clear explanations and examples, especially
related to technology and future work, are sought to correctly evaluate titles.\\\",
\\\"coworker\\\": \\\"Scorer\\\"}\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 676,\n \"completion_tokens\": 303,\n
\ \"total_tokens\": 979,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3bf709da7ba4ca-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 15 Sep 2024 22:13:47 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:
- '10074'
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_a4fa3852002703190519343ad106ab40
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: Can you explain the
criteria used to assign a score between 1-5 to a title? Specifically, I''m interested
in understanding what aspects or qualities of a title would make it score at
each level of this scale. The task at hand involves scoring the title ''The
impact of AI in the future of work'', so examples relevant to technology or
future-oriented themes would be especially helpful.\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:\nA
score needs to be assigned to the title ''The impact of AI in the future of
work'', based on its relevance, impact, originality, and clarity. The scoring
system ranges from 1 to 5, but the precise criteria for what constitutes each
score level hasn''t been specified. Clear explanations and examples, especially
related to technology and future work, are sought to correctly evaluate titles.\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:
- '2207'
content-type:
- application/json
cookie:
- __cf_bm=xCQEG8vgEvQfut0bkj2xgre9z9ePZhdKdNxBphhvH6s-1726437753-1.0.1.1-5qo0zwDCcKDtqvIzDbp2sLEPCey8v5DAsf0Mg6f2RmooOW9FXTw2P66VCTTF.vCwTpWBIFk0vzKmBAPOt6urIg;
_cfuvid=TiTyEciy7HrUlIDEsELZqkUyM4Fyn8OldZd4JefFMOA-1726437753108-0.0.1.1-604800000
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-A7rn1t222OXqmXGd9iBf7QoiWmPcL\",\n \"object\":
\"chat.completion\",\n \"created\": 1726438427,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to obtain examples of
how titles are scored to understand the criteria for assigning scores between
1 and 5. These examples should ideally be related to technology and future-oriented
themes.\\n\\nAction: scoring_examples\\nAction Input: {}\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 433,\n \"completion_tokens\":
48,\n \"total_tokens\": 481,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3bf74ab95fa4ca-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 15 Sep 2024 22:13:47 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:
- '499'
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:
- '29999469'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_349e72cf9271c787025e996bf10ce42f
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: Can you explain the
criteria used to assign a score between 1-5 to a title? Specifically, I''m interested
in understanding what aspects or qualities of a title would make it score at
each level of this scale. The task at hand involves scoring the title ''The
impact of AI in the future of work'', so examples relevant to technology or
future-oriented themes would be especially helpful.\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:\nA
score needs to be assigned to the title ''The impact of AI in the future of
work'', based on its relevance, impact, originality, and clarity. The scoring
system ranges from 1 to 5, but the precise criteria for what constitutes each
score level hasn''t been specified. Clear explanations and examples, especially
related to technology and future work, are sought to correctly evaluate titles.\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 obtain examples of how titles are scored to understand the
criteria for assigning scores between 1 and 5. These examples should ideally
be related to technology and future-oriented themes.\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:
- '3303'
content-type:
- application/json
cookie:
- __cf_bm=xCQEG8vgEvQfut0bkj2xgre9z9ePZhdKdNxBphhvH6s-1726437753-1.0.1.1-5qo0zwDCcKDtqvIzDbp2sLEPCey8v5DAsf0Mg6f2RmooOW9FXTw2P66VCTTF.vCwTpWBIFk0vzKmBAPOt6urIg;
_cfuvid=TiTyEciy7HrUlIDEsELZqkUyM4Fyn8OldZd4JefFMOA-1726437753108-0.0.1.1-604800000
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-A7rn2kHS1KtaUeBSW6LFHrEBYtq87\",\n \"object\":
\"chat.completion\",\n \"created\": 1726438428,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to attempt using the
tool again to obtain examples for scoring titles, as these are crucial to give
a complete and accurate answer.\\n\\nAction: scoring_examples\\nAction Input:
{}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 659,\n \"completion_tokens\":
38,\n \"total_tokens\": 697,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3bf74fb844a4ca-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 15 Sep 2024 22:13:48 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:
- '466'
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:
- '29999208'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_87d530d6877e9a31b78ffbaa6cdfb071
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: Can you explain the
criteria used to assign a score between 1-5 to a title? Specifically, I''m interested
in understanding what aspects or qualities of a title would make it score at
each level of this scale. The task at hand involves scoring the title ''The
impact of AI in the future of work'', so examples relevant to technology or
future-oriented themes would be especially helpful.\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:\nA
score needs to be assigned to the title ''The impact of AI in the future of
work'', based on its relevance, impact, originality, and clarity. The scoring
system ranges from 1 to 5, but the precise criteria for what constitutes each
score level hasn''t been specified. Clear explanations and examples, especially
related to technology and future work, are sought to correctly evaluate titles.\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 obtain examples of how titles are scored to understand the
criteria for assigning scores between 1 and 5. These examples should ideally
be related to technology and future-oriented themes.\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 need to attempt using the tool
again to obtain examples for scoring titles, as these are crucial to give a
complete and accurate answer.\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:
- '4339'
content-type:
- application/json
cookie:
- __cf_bm=xCQEG8vgEvQfut0bkj2xgre9z9ePZhdKdNxBphhvH6s-1726437753-1.0.1.1-5qo0zwDCcKDtqvIzDbp2sLEPCey8v5DAsf0Mg6f2RmooOW9FXTw2P66VCTTF.vCwTpWBIFk0vzKmBAPOt6urIg;
_cfuvid=TiTyEciy7HrUlIDEsELZqkUyM4Fyn8OldZd4JefFMOA-1726437753108-0.0.1.1-604800000
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-A7rn3LOdwrTNy4G8DnyWQBmBhTQTt\",\n \"object\":
\"chat.completion\",\n \"created\": 1726438429,\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
tool again by providing the correct input format.\\n\\nAction: scoring_examples\\nAction
Input: {}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
875,\n \"completion_tokens\": 26,\n \"total_tokens\": 901,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3bf7549f38a4ca-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 15 Sep 2024 22:13:49 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:
- '337'
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:
- '29998962'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_724b4f2182156491bb759ce65e983275
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
CvsCCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS0gIKEgoQY3Jld2FpLnRl
bGVtZXRyeRJoChD/PK+BwEa94jnmgYBrvN3SEghFjDD48hzlgioQVG9vbCBVc2FnZSBFcnJvcjAB
Ocje31+aivUXQaD86V+aivUXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuNTYuMHoCGAGFAQABAAAS
aAoQKpCfervz4UKBHzjG/rxfsxII8A+p20EupwMqEFRvb2wgVXNhZ2UgRXJyb3IwATkgQGGOmor1
F0HQ4WSOmor1F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjU2LjB6AhgBhQEAAQAAEmgKELx9oOWQ
gA6FizMPxbBstewSCN047wIsTXoeKhBUb29sIFVzYWdlIEVycm9yMAE54PoptJqK9RdByGMutJqK
9RdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC41Ni4wegIYAYUBAAEAAA==
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '382'
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:
- Sun, 15 Sep 2024 22:13:50 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: Can you explain the
criteria used to assign a score between 1-5 to a title? Specifically, I''m interested
in understanding what aspects or qualities of a title would make it score at
each level of this scale. The task at hand involves scoring the title ''The
impact of AI in the future of work'', so examples relevant to technology or
future-oriented themes would be especially helpful.\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:\nA
score needs to be assigned to the title ''The impact of AI in the future of
work'', based on its relevance, impact, originality, and clarity. The scoring
system ranges from 1 to 5, but the precise criteria for what constitutes each
score level hasn''t been specified. Clear explanations and examples, especially
related to technology and future work, are sought to correctly evaluate titles.\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 obtain examples of how titles are scored to understand the
criteria for assigning scores between 1 and 5. These examples should ideally
be related to technology and future-oriented themes.\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 need to attempt using the tool
again to obtain examples for scoring titles, as these are crucial to give a
complete and accurate answer.\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 tool again by
providing the correct input format.\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:
- '5314'
content-type:
- application/json
cookie:
- __cf_bm=xCQEG8vgEvQfut0bkj2xgre9z9ePZhdKdNxBphhvH6s-1726437753-1.0.1.1-5qo0zwDCcKDtqvIzDbp2sLEPCey8v5DAsf0Mg6f2RmooOW9FXTw2P66VCTTF.vCwTpWBIFk0vzKmBAPOt6urIg;
_cfuvid=TiTyEciy7HrUlIDEsELZqkUyM4Fyn8OldZd4JefFMOA-1726437753108-0.0.1.1-604800000
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-A7rn37YY72GoOpEMIiCUmU307BiVl\",\n \"object\":
\"chat.completion\",\n \"created\": 1726438429,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: Given that I am unable to access
the scoring_examples tool, I will rely on my expertise to provide a detailed
answer based on the standard criteria for scoring titles.\\n\\nFinal Answer:
Here is your detailed answer on how to score a title between 1 and 5, specifically
for the title 'The impact of AI in the future of work':\\n\\n1. **Relevance**:\\n
\ - **Score 1**: The title is completely irrelevant to the given context or
topic.\\n - **Score 2**: The title has limited relevance, touching only tangentially
on the topic.\\n - **Score 3**: The title is moderately relevant but lacks
focus or specificity.\\n - **Score 4**: The title is relevant and addresses
the topic directly with clear focus.\\n - **Score 5**: The title is highly
relevant, directly addressing the core topic comprehensively and precisely.\\n\\n2.
**Impact**:\\n - **Score 1**: The title suggests minimal or no significant
impact on the reader or the field.\\n - **Score 2**: The title indicates
some impact but does not clearly convey its significance.\\n - **Score 3**:
The title reflects a moderate impact, highlighting importance but lacking strong
emphasis.\\n - **Score 4**: The title conveys a strong impact, clearly indicating
its importance to the field.\\n - **Score 5**: The title suggests a profound
impact, compelling the reader with a sense of urgency or significance.\\n\\n3.
**Originality**:\\n - **Score 1**: The title is generic, common, or overused,
with no original contribution.\\n - **Score 2**: The title shows minimal
originality, being slightly more specific than a generic title.\\n - **Score
3**: The title has some original elements but may still feel somewhat familiar.\\n
\ - **Score 4**: The title is original, presenting a fresh perspective on
the topic.\\n - **Score 5**: The title is highly original, offering a unique
and innovative approach or angle.\\n\\n4. **Clarity**:\\n - **Score 1**:
The title is confusing, ambiguous, or poorly worded.\\n - **Score 2**: The
title is somewhat clear but may contain jargon or unclear elements.\\n -
**Score 3**: The title is reasonably clear but could be more concise or straightforward.\\n
\ - **Score 4**: The title is clear, well-structured, and easy to understand.\\n
\ - **Score 5**: The title is exceptionally clear, concise, and leaves no
room for misinterpretation.\\n\\n**Example Application:**\\n\\nFor the title
'The impact of AI in the future of work', let's evaluate it based on the given
criteria:\\n\\n- **Relevance**: 5 (Highly relevant as it directly addresses
the topic of AI and its role in the future workplace)\\n- **Impact**: 4 (Conveys
strong impact, emphasizing the importance of AI in future work scenarios)\\n-
**Originality**: 3 (Moderately original; it is specific but the theme of AI
and future work is widely discussed)\\n- **Clarity**: 4 (Clear and straightforward
but could perhaps be more concise by rephrasing)\\n\\nOverall Score: This title
could be rated around a 4, as it effectively communicates its relevance, impact,
and clarity, but with room for slight improvement in originality and specificity.\\n\\nThis
detailed explanation should help you understand how to evaluate and score titles
effectively across different criteria.\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 1079,\n \"completion_tokens\": 723,\n
\ \"total_tokens\": 1802,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3bf7588c05a4ca-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 15 Sep 2024 22:13:56 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '6345'
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:
- '29998730'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_7db731cf7c3002a7d8a6782e8be05509
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
CtsBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSsgEKEgoQY3Jld2FpLnRl
bGVtZXRyeRKbAQoQYEhRgslsu3bVH9xRWEA0BhIICcgmLW3l7DoqClRvb2wgVXNhZ2UwATkA2vw/
nIr1F0EAFQhAnIr1F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjU2LjBKJwoJdG9vbF9uYW1lEhoK
GEFzayBxdWVzdGlvbiB0byBjb3dvcmtlckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAA
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '222'
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:
- Sun, 15 Sep 2024 22:14:00 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 evaluate the given title ''The impact of AI in the future
of work'' against the specified criteria (an integer score between 1-5), I need
to understand the criteria that my coworker, Scorer, will use for assessment.
This involves knowing what makes a title score a 1 versus a 5 and any gradations
in between. I should gather all available context regarding this scoring system
before delegating the task of scoring the title to Scorer. It''s important to
make sure the evaluation criteria are clear to ensure the scoring process aligns
with the expectations.\n\nAction: Ask question to coworker\n\nAction Input:
{\"question\": \"Can you explain the criteria used to assign a score between
1-5 to a title? Specifically, I''m interested in understanding what aspects
or qualities of a title would make it score at each level of this scale. The
task at hand involves scoring the title ''The impact of AI in the future of
work'', so examples relevant to technology or future-oriented themes would be
especially helpful.\", \"context\": \"A score needs to be assigned to the title
''The impact of AI in the future of work'', based on its relevance, impact,
originality, and clarity. The scoring system ranges from 1 to 5, but the precise
criteria for what constitutes each score level hasn''t been specified. Clear
explanations and examples, especially related to technology and future work,
are sought to correctly evaluate titles.\", \"coworker\": \"Scorer\"}\nObservation:
Here is your detailed answer on how to score a title between 1 and 5, specifically
for the title ''The impact of AI in the future of work'':\n\n1. **Relevance**:\n -
**Score 1**: The title is completely irrelevant to the given context or topic.\n -
**Score 2**: The title has limited relevance, touching only tangentially on
the topic.\n - **Score 3**: The title is moderately relevant but lacks focus
or specificity.\n - **Score 4**: The title is relevant and addresses the
topic directly with clear focus.\n - **Score 5**: The title is highly relevant,
directly addressing the core topic comprehensively and precisely.\n\n2. **Impact**:\n -
**Score 1**: The title suggests minimal or no significant impact on the reader
or the field.\n - **Score 2**: The title indicates some impact but does not
clearly convey its significance.\n - **Score 3**: The title reflects a moderate
impact, highlighting importance but lacking strong emphasis.\n - **Score
4**: The title conveys a strong impact, clearly indicating its importance to
the field.\n - **Score 5**: The title suggests a profound impact, compelling
the reader with a sense of urgency or significance.\n\n3. **Originality**:\n -
**Score 1**: The title is generic, common, or overused, with no original contribution.\n -
**Score 2**: The title shows minimal originality, being slightly more specific
than a generic title.\n - **Score 3**: The title has some original elements
but may still feel somewhat familiar.\n - **Score 4**: The title is original,
presenting a fresh perspective on the topic.\n - **Score 5**: The title is
highly original, offering a unique and innovative approach or angle.\n\n4. **Clarity**:\n -
**Score 1**: The title is confusing, ambiguous, or poorly worded.\n - **Score
2**: The title is somewhat clear but may contain jargon or unclear elements.\n -
**Score 3**: The title is reasonably clear but could be more concise or straightforward.\n -
**Score 4**: The title is clear, well-structured, and easy to understand.\n -
**Score 5**: The title is exceptionally clear, concise, and leaves no room for
misinterpretation.\n\n**Example Application:**\n\nFor the title ''The impact
of AI in the future of work'', let''s evaluate it based on the given criteria:\n\n-
**Relevance**: 5 (Highly relevant as it directly addresses the topic of AI and
its role in the future workplace)\n- **Impact**: 4 (Conveys strong impact, emphasizing
the importance of AI in future work scenarios)\n- **Originality**: 3 (Moderately
original; it is specific but the theme of AI and future work is widely discussed)\n-
**Clarity**: 4 (Clear and straightforward but could perhaps be more concise
by rephrasing)\n\nOverall Score: This title could be rated around a 4, as it
effectively communicates its relevance, impact, and clarity, but with room for
slight improvement in originality and specificity.\n\nThis detailed explanation
should help you understand how to evaluate and score titles effectively across
different criteria."}], "model": "gpt-4-0125-preview", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '7633'
content-type:
- application/json
cookie:
- __cf_bm=xCQEG8vgEvQfut0bkj2xgre9z9ePZhdKdNxBphhvH6s-1726437753-1.0.1.1-5qo0zwDCcKDtqvIzDbp2sLEPCey8v5DAsf0Mg6f2RmooOW9FXTw2P66VCTTF.vCwTpWBIFk0vzKmBAPOt6urIg;
_cfuvid=TiTyEciy7HrUlIDEsELZqkUyM4Fyn8OldZd4JefFMOA-1726437753108-0.0.1.1-604800000
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-A7rnAEjmu1Z22PltyaBJL8seuiyJx\",\n \"object\":
\"chat.completion\",\n \"created\": 1726438436,\n \"model\": \"gpt-4-0125-preview\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: With the detailed criteria provided
by Scorer on how to score a title between 1 to 5, focusing on relevance, impact,
originality, and clarity, I now have a clear framework to evaluate the title
'The impact of AI in the future of work'. According to the explanation, this
title aligns closely with the highest standards of relevance and has a strong
impact, while its originality is moderate in the current discourse and its clarity
is considered high. Based on these insights, I can deduce an appropriate score
that balances these factors, keeping in mind the provided example application
which suggests a score of 4. This aligns closely with the evaluation and scoring
framework described by Scorer. The example given by Scorer explicitly evaluated
the title in question, providing sufficient rationale for a score. So, I can
confidently finalize my decision without further delegation.\\n\\nI now know
the final answer.\\n\\nFinal Answer: The score for the title 'The impact of
AI in the future of work' is 4. This score is based on its high relevance to
the topic, strong impact indicating its importance to the field, moderate originality
considering the wide discussion on AI and work, and high clarity in its expression.\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 1653,\n \"completion_tokens\":
244,\n \"total_tokens\": 1897,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3bf78229b7a4ca-MIA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 15 Sep 2024 22:14:04 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:
- '8312'
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:
- '1998139'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 55ms
x-request-id:
- req_4d766138e37b0347f3d356bd6252f972
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink