andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-05-03 00:02:36 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Making all tests good

Browse Source
This commit is contained in:
João Moura
2024-09-13 04:30:11 -05:00
parent 7120a9860b
commit 91ddab207f
88 changed files with 28070 additions and 26873 deletions
Download Patch File Download Diff File Expand all files Collapse all files

568
tests/cassettes/test_output_json_hierarchical.yaml
View File

@@ -1,7 +1,7 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are Crew Manager. You are
a seasoned manager with a knack for getting the best out of your team.\nYou
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
@@ -32,13 +32,13 @@ interactions:
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n\nCurrent Task: Give me an
integer score between 1-5 for the following title: ''The impact of AI in the
future of work''\n\nThis is the expect criteria for your final answer: The score
of the title. \n you MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
"gpt-4o", "stop": ["\nObservation"]}'
the final answer to the original input question\n"}, {"role": "user", "content":
"\nCurrent Task: Give me an integer score between 1-5 for the following title:
''The impact of AI in the future of work''\n\nThis is the expect criteria for
your final answer: The score of the title.\nyou MUST return the actual complete
content as the final answer, not a summary.\n\nBegin! This is VERY important
to you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
@@ -47,16 +47,16 @@ interactions:
connection:
- keep-alive
content-length:
- '2980'
- '3013'
content-type:
- application/json
cookie:
- _cfuvid=8r8yFLG2b7e3n6pklgpsT05MHRvfdePz1ckAFvRQY8E-1725949790252-0.0.1.1-604800000;
__cf_bm=fuuc.ZDO3Y9B7nXE_8fBn7ykDAvAaK1VdxjZw0MTtsE-1725949790-1.0.1.1-pAJ7BWJMj1j3gS2ySR6xSBO7uFrjcB6ehFra4QVq14JqaiG4VDIjDO1C3WueKGRnSALSkpLQyJcJ2YVd_pXglQ
- __cf_bm=pgsskMPipgeSB6HhnkjwcOEfengIvt0p9whKNmTJVLs-1726215280-1.0.1.1-Gtqb.nO1U.cHTnd9mR9sEA5tpVo1.pexRrxqXOkn.6Mzja8mLG1URJsOLTfjMAAYpWaUQe4Rjmnr6lqQk5hAxQ;
_cfuvid=dp2yoCmGHVlURh_U78_UoIfnhcO5UhufnL5whkUSMTQ-1726214380689-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
@@ -66,7 +66,7 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
- 1.45.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
@@ -76,27 +76,25 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A5oiGZtyGVDA0w9otj9rbpbQg03km\",\n \"object\":
\"chat.completion\",\n \"created\": 1725949944,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-A6vo3vU9icQjgyCm9qyGlTj79kY23\",\n \"object\":
\"chat.completion\",\n \"created\": 1726215539,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"To determine the appropriate score for
the title \\\"The impact of AI in the future of work,\\\" I need to involve
our Scorer. I will delegate the task to them with detailed context to ensure
they provide an accurate score.\\n\\nAction: Delegate work to coworker\\nAction
Input: {\\\"task\\\": \\\"Give an integer score between 1-5 for the following
title: 'The impact of AI in the future of work'\\\", \\\"context\\\": \\\"We
need to score the title based on its relevance, clarity, and appeal. A score
of 1 means the title is poor, while a score of 5 means the title is excellent.
Consider factors like how well the title encapsulates a relevant and engaging
topic.\\\", \\\"coworker\\\": \\\"Scorer\\\"}\\n\",\n \"refusal\": null\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 660,\n \"completion_tokens\":
152,\n \"total_tokens\": 812\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
\"assistant\",\n \"content\": \"I need to delegate this task to the appropriate
coworker, Scorer, who will provide a score based on the given title and the
provided context.\\n\\nAction: Delegate work to coworker\\nAction Input: {\\\"task\\\":
\\\"Give an integer score between 1-5 for the following title: 'The impact of
AI in the future of work'\\\", \\\"context\\\": \\\"The scoring criteria requires
providing an integer score between 1-5 for the title 'The impact of AI in the
future of work'.\\\", \\\"coworker\\\": \\\"Scorer\\\"}\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 664,\n \"completion_tokens\":
111,\n \"total_tokens\": 775,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c0d61704856cf35-SJC
- 8c26b5aefbdb2ab9-LAX
Connection:
- keep-alive
Content-Encoding:
@@ -104,7 +102,7 @@ interactions:
Content-Type:
- application/json
Date:
- Tue, 10 Sep 2024 06:32:26 GMT
- Fri, 13 Sep 2024 08:19:01 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -118,7 +116,7 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1819'
- '1295'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -130,31 +128,243 @@ interactions:
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999270'
- '29999269'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_6097fa7f18f573d36a8c58d387e6b174
- req_cc3a8d5efc0b6a6b7565354e6b40544c
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are Scorer. You''re an expert
scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo
give my best complete final answer to the task use the exact following format:\n\nThought:
I now can give a great answer\nFinal Answer: Your final answer must be the great
and the most complete as possible, it must be outcome described.\n\nI MUST use
these formats, my job depends on it!\nCurrent Task: Give an integer score between
1-5 for the following title: ''The impact of AI in the future of work''\n\nThis
is the expect criteria for your final answer: Your best answer to your coworker
asking you this, accounting for the context shared. \n you MUST return the actual
complete content as the final answer, not a summary.\n\nThis is the context
you''re working with:\nWe need to score the title based on its relevance, clarity,
and appeal. A score of 1 means the title is poor, while a score of 5 means the
title is excellent. Consider factors like how well the title encapsulates a
relevant and engaging topic.\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:"}],
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '2460'
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:
- Fri, 13 Sep 2024 08:19:01 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\nTo give my best complete final answer to the task use the exact following
format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
answer must be the great and the most complete as possible, it must be outcome
described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
"content": "\nCurrent Task: Give an integer score between 1-5 for the following
title: ''The impact of AI in the future of work''\n\nThis is the expect criteria
for your final answer: Your best answer to your coworker asking you this, accounting
for the context shared.\nyou MUST return the actual complete content as the
final answer, not a summary.\n\nThis is the context you''re working with:\nThe
scoring criteria requires providing an integer score between 1-5 for the title
''The impact of AI in the future of work''.\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:
- '1171'
content-type:
- application/json
cookie:
- __cf_bm=pgsskMPipgeSB6HhnkjwcOEfengIvt0p9whKNmTJVLs-1726215280-1.0.1.1-Gtqb.nO1U.cHTnd9mR9sEA5tpVo1.pexRrxqXOkn.6Mzja8mLG1URJsOLTfjMAAYpWaUQe4Rjmnr6lqQk5hAxQ;
_cfuvid=dp2yoCmGHVlURh_U78_UoIfnhcO5UhufnL5whkUSMTQ-1726214380689-0.0.1.1-604800000
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-A6vo6gXtj6K8zyjv3QD5usKrYdroc\",\n \"object\":
\"chat.completion\",\n \"created\": 1726215542,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: 4\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
231,\n \"completion_tokens\": 15,\n \"total_tokens\": 246,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26b5c039f42ab9-LAX
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:19:02 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:
- '288'
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:
- '29999724'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_5c2b1173341406b0c5918edff08a5a5e
http_version: HTTP/1.1
status_code: 200
- 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''\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": "I need to delegate this
task to the appropriate coworker, Scorer, who will provide a score based on
the given title and the provided context.\n\nAction: Delegate work to coworker\nAction
Input: {\"task\": \"Give an integer score between 1-5 for the following title:
''The impact of AI in the future of work''\", \"context\": \"The scoring criteria
requires providing an integer score between 1-5 for the title ''The impact of
AI in the future of work''.\", \"coworker\": \"Scorer\"}\nObservation: 4"}],
"model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
@@ -164,16 +374,16 @@ interactions:
connection:
- keep-alive
content-length:
- '1257'
- '3545'
content-type:
- application/json
cookie:
- _cfuvid=8r8yFLG2b7e3n6pklgpsT05MHRvfdePz1ckAFvRQY8E-1725949790252-0.0.1.1-604800000;
__cf_bm=fuuc.ZDO3Y9B7nXE_8fBn7ykDAvAaK1VdxjZw0MTtsE-1725949790-1.0.1.1-pAJ7BWJMj1j3gS2ySR6xSBO7uFrjcB6ehFra4QVq14JqaiG4VDIjDO1C3WueKGRnSALSkpLQyJcJ2YVd_pXglQ
- __cf_bm=pgsskMPipgeSB6HhnkjwcOEfengIvt0p9whKNmTJVLs-1726215280-1.0.1.1-Gtqb.nO1U.cHTnd9mR9sEA5tpVo1.pexRrxqXOkn.6Mzja8mLG1URJsOLTfjMAAYpWaUQe4Rjmnr6lqQk5hAxQ;
_cfuvid=dp2yoCmGHVlURh_U78_UoIfnhcO5UhufnL5whkUSMTQ-1726214380689-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
@@ -183,7 +393,7 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
- 1.45.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
@@ -193,172 +403,19 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A5oiJ9AHm2wZYXheSKPeTFKrUmR29\",\n \"object\":
\"chat.completion\",\n \"created\": 1725949947,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: 4\\n\\nThe title 'The impact of AI in the future of work' scores a 4.
It is highly relevant, as artificial intelligence is a significant and timely
topic affecting various aspects of work and industry. The title is clear and
concise, immediately indicating the focus on AI's role in shaping future work
environments. It is appealing because it touches on both technology and its
implications, which are pertinent to a wide audience. However, it could be slightly
more specific to achieve a perfect score.\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 254,\n \"completion_tokens\": 112,\n
\ \"total_tokens\": 366\n },\n \"system_fingerprint\": \"fp_157b3831f5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c0d61804a17cf35-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 10 Sep 2024 06:32:28 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:
- '1550'
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:
- '29999696'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_846b42e87a818ed85d04450086d6e2e2
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are Crew Manager. You are
a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Delegate work to coworker(task: str, context:
str, coworker: Optional[str] = None, **kwargs)\nTool Description: Delegate a
specific task to one of the following coworkers: Scorer\nThe input to this tool
should be the coworker, the task you want them to do, and ALL necessary context
to execute the task, they know nothing about the task, so share absolute everything
you know, don''t reference things but instead explain them.\nTool Arguments:
{''task'': {''title'': ''Task'', ''type'': ''string''}, ''context'': {''title'':
''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'',
''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\nTool
Name: Ask question to coworker(question: str, context: str, coworker: Optional[str]
= None, **kwargs)\nTool Description: Ask a specific question to one of the following
coworkers: Scorer\nThe input to this tool should be the coworker, the question
you have for them, and ALL necessary context to ask the question properly, they
know nothing about the question, so share absolute everything you know, don''t
reference things but instead explain them.\nTool Arguments: {''question'': {''title'':
''Question'', ''type'': ''string''}, ''context'': {''title'': ''Context'', ''type'':
''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''},
''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, only one name of [Delegate work to coworker, Ask question to coworker],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n\nCurrent Task: Give me an
integer score between 1-5 for the following title: ''The impact of AI in the
future of work''\n\nThis is the expect criteria for your final answer: The score
of the title. \n you MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}, {"role":
"assistant", "content": "To determine the appropriate score for the title \"The
impact of AI in the future of work,\" I need to involve our Scorer. I will delegate
the task to them with detailed context to ensure they provide an accurate score.\n\nAction:
Delegate work to coworker\nAction Input: {\"task\": \"Give an integer score
between 1-5 for the following title: ''The impact of AI in the future of work''\",
\"context\": \"We need to score the title based on its relevance, clarity, and
appeal. A score of 1 means the title is poor, while a score of 5 means the title
is excellent. Consider factors like how well the title encapsulates a relevant
and engaging topic.\", \"coworker\": \"Scorer\"}\n\nObservation: 4\n\nThe title
''The impact of AI in the future of work'' scores a 4. It is highly relevant,
as artificial intelligence is a significant and timely topic affecting various
aspects of work and industry. The title is clear and concise, immediately indicating
the focus on AI''s role in shaping future work environments. It is appealing
because it touches on both technology and its implications, which are pertinent
to a wide audience. However, it could be slightly more specific to achieve a
perfect score."}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '4212'
content-type:
- application/json
cookie:
- _cfuvid=8r8yFLG2b7e3n6pklgpsT05MHRvfdePz1ckAFvRQY8E-1725949790252-0.0.1.1-604800000;
__cf_bm=fuuc.ZDO3Y9B7nXE_8fBn7ykDAvAaK1VdxjZw0MTtsE-1725949790-1.0.1.1-pAJ7BWJMj1j3gS2ySR6xSBO7uFrjcB6ehFra4QVq14JqaiG4VDIjDO1C3WueKGRnSALSkpLQyJcJ2YVd_pXglQ
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A5oiLXBB53MvwRHVSPLYlQhvMsKBU\",\n \"object\":
\"chat.completion\",\n \"created\": 1725949949,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-A6vo86zudLtcpce5wPVOMlN5RK7jU\",\n \"object\":
\"chat.completion\",\n \"created\": 1726215544,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now know the final answer.\\nFinal
Answer: 4\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
917,\n \"completion_tokens\": 14,\n \"total_tokens\": 931\n },\n \"system_fingerprint\":
\"fp_25624ae3a5\"\n}\n"
783,\n \"completion_tokens\": 14,\n \"total_tokens\": 797,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c0d618bd907cf35-SJC
- 8c26b5cc9d152ab9-LAX
Connection:
- keep-alive
Content-Encoding:
@@ -366,7 +423,7 @@ interactions:
Content-Type:
- application/json
Date:
- Tue, 10 Sep 2024 06:32:29 GMT
- Fri, 13 Sep 2024 08:19:04 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -380,7 +437,7 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '276'
- '242'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -392,24 +449,57 @@ interactions:
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29998974'
- '29999148'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
- 1ms
x-request-id:
- req_8f1a7115d850a517128e4a5d2ebac10f
- req_1083e78467b4037ee0a744fb4d7bebc0
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
CtwBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSswEKEgoQY3Jld2FpLnRl
bGVtZXRyeRKcAQoQQU6eA2kvNicssnwHwQdexhIIayvWto+TmdMqClRvb2wgVXNhZ2UwATnAH3mw
47/0F0EIc36w47/0F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjU2LjBKKAoJdG9vbF9uYW1lEhsK
GURlbGVnYXRlIHdvcmsgdG8gY293b3JrZXJKDgoIYXR0ZW1wdHMSAhgBegIYAYUBAAEAAA==
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '223'
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:
- Fri, 13 Sep 2024 08:19:06 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "4"}, {"role": "system", "content":
"I''m gonna convert this raw text into valid JSON.\n\nThe json should have the
following structure, with the following keys:\n{\n score: int\n}"}], "model":
"gpt-4o", "tool_choice": {"type": "function", "function": {"name": "ScoreOutput"}},
"tools": [{"type": "function", "function": {"name": "ScoreOutput", "description":
"Correctly extracted `ScoreOutput` with all the required parameters with correct
types", "parameters": {"properties": {"score": {"title": "Score", "type": "integer"}},
"required": ["score"], "type": "object"}}}]}'
"I''m gonna convert this raw text into valid JSON."}], "model": "gpt-4o", "tool_choice":
{"type": "function", "function": {"name": "ScoreOutput"}}, "tools": [{"type":
"function", "function": {"name": "ScoreOutput", "description": "Correctly extracted
`ScoreOutput` with all the required parameters with correct types", "parameters":
{"properties": {"score": {"title": "Score", "type": "integer"}}, "required":
["score"], "type": "object"}}}]}'
headers:
accept:
- application/json
@@ -418,16 +508,16 @@ interactions:
connection:
- keep-alive
content-length:
- '615'
- '519'
content-type:
- application/json
cookie:
- __cf_bm=B5UEX82SlhFAhiEbobEv42vqC_s0jiOE9..GEHd2PM8-1725949937-1.0.1.1-jazIEvwLe8YXt0Xldxw5V3Dm50joI_ajSaDngSFCWqVdgRm3rJxeYip55y1JxFf90tlPQWlc28VZLg5QpQUNcA;
_cfuvid=yMG4HwMFIQbW20zb7f_ElvINxRtWnRbaaUVp1YqP5vY-1725949937391-0.0.1.1-604800000
- __cf_bm=n_BvuurPQNYmr4Xe9Yg_foBSFxwgwMpaTEdPHdqVgGQ-1726214721-1.0.1.1-WYudPPoSnx6FZSF9AMgWsJ8MlooxW8CnQiO2OS.lbnFdxsvYvd08ZsU2GLr1qne3Wxw6ebt_7iRVpoFdpAvarA;
_cfuvid=rXgn0vlVZcDxXcw1CtGMaLx8.GKpg0HOhhM.Ai36L2I-1726214721376-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
@@ -437,7 +527,7 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
- 1.45.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
@@ -447,22 +537,22 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A5oiLauxef1zJZb7fZgwa54LZx0UV\",\n \"object\":
\"chat.completion\",\n \"created\": 1725949949,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-A6voBKUyaIcDsq37nO0iBGKcZF4HG\",\n \"object\":
\"chat.completion\",\n \"created\": 1726215547,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_6v3iTXG0u3Hneuvq148KaGga\",\n \"type\":
\ \"id\": \"call_OTDUFkmUlCmThqY34t9Dnuof\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"ScoreOutput\",\n
\ \"arguments\": \"{\\\"score\\\":4}\"\n }\n }\n
\ ],\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
100,\n \"completion_tokens\": 5,\n \"total_tokens\": 105\n },\n \"system_fingerprint\":
\"fp_25624ae3a5\"\n}\n"
80,\n \"completion_tokens\": 5,\n \"total_tokens\": 85,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c0d6192580e17e8-SJC
- 8c26b5dffe227e8f-LAX
Connection:
- keep-alive
Content-Encoding:
@@ -470,7 +560,7 @@ interactions:
Content-Type:
- application/json
Date:
- Tue, 10 Sep 2024 06:32:30 GMT
- Fri, 13 Sep 2024 08:19:07 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -484,7 +574,7 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '171'
- '475'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -496,13 +586,13 @@ interactions:
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999947'
- '29999968'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_09241c40c367f00f3803552b1c1c5be7
- req_1096ac0405bd16b97e747c5f2d6b9b06
http_version: HTTP/1.1
status_code: 200
version: 1