andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-09 08:08:32 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
Files
7120a9860bb49f47df9caf23f2d27554a1e0440a
crewAI/tests/cassettes/test_increment_delegations_for_sequential_process.yaml
João Moura 7120a9860b removing langchain
2024-09-13 04:38:19 -05:00

442 lines
20 KiB
YAML
Raw Blame History

interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are Manager. You''re great
at delegating work about scoring.\nYour personal goal is: Coordinate scoring
processes\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:"}], "model":
"gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2607'
content-type:
- application/json
cookie:
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A6Z33vxoIkYm0m4jSbwym7Wc3Vxm8\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128057,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I need to coordinate the scoring process
for the title \\\"The impact of AI in the future of work\\\". I will delegate
this task to the Scorer, providing them with all the necessary context and details
for scoring.\\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\\\": \\\"Please score the title based
on its relevance, clarity, and potential impact in the context of the future
of work. Consider factors such as current trends in AI, its applications in
the workplace, and possible future advancements.\\\", \\\"coworker\\\": \\\"Scorer\\\"}\\n\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 580,\n \"completion_tokens\":
139,\n \"total_tokens\": 719\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5de67e2e6280-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:01:00 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:
- '2637'
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:
- '29999361'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_f207cc3e7d94e0883825e3595ea8a96a
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:\nPlease score the title based on its relevance, clarity,
and potential impact in the context of the future of work. Consider factors
such as current trends in AI, its applications in the workplace, and possible
future advancements.\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:
- '1244'
content-type:
- application/json
cookie:
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A6Z36jzKD4rmMvTw7b9GqEV6nUg2p\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128060,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer\\nFinal
Answer: 5\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
243,\n \"completion_tokens\": 13,\n \"total_tokens\": 256\n },\n \"system_fingerprint\":
\"fp_157b3831f5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5df9cea56280-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:01:01 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:
- '362'
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:
- '29999698'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_af608b3b93f27393f27d907adb216e3e
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1730'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Thu, 12 Sep 2024 08:01:01 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "You are Manager. You''re great
at delegating work about scoring.\nYour personal goal is: Coordinate scoring
processes\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": "I need to coordinate the scoring process for the title
\"The impact of AI in the future of work\". I will delegate this task to the
Scorer, providing them with all the necessary context and details for scoring.\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\": \"Please score the title based on its relevance, clarity, and potential
impact in the context of the future of work. Consider factors such as current
trends in AI, its applications in the workplace, and possible future advancements.\",
\"coworker\": \"Scorer\"}\n\nObservation: 5"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3316'
content-type:
- application/json
cookie:
- _cfuvid=wl8o2jxCEnNABWV8zufHzNbIUfqCUxybX7Vi.1Ga1Zw-1726128032785-0.0.1.1-604800000;
__cf_bm=P6UUFPZt3p6lqd7cohlJaH8_cHJme92vyvYAbmz9NJM-1726128032-1.0.1.1-SpOib44J8vNLUjryxJjCeKWYWh49FWI5zpJ4UI1znYGWjRzK.vHdTx9WD07B3165P6KCStQUSxIsZNjVxE16Cg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A6Z37Cj4kDP8u0Z5wTOuzSyQ7cH5q\",\n \"object\":
\"chat.completion\",\n \"created\": 1726128061,\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: 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\": 727,\n \"completion_tokens\":
32,\n \"total_tokens\": 759\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c1e5dff78bb6280-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Sep 2024 08:01:02 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:
- '669'
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:
- '29999197'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_a1c97d3f0bdf96af5454b71ba6912703
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink