mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-08 23:58:34 +00:00
ea7759b322
This now will allow to add a max_inter option to agents while also making sure to force the agent to give it's best final answer before running out of it's max_inter.
443 lines
16 KiB
YAML
443 lines
16 KiB
YAML
interactions:
|
|
- request:
|
|
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
|
|
personal goal is: test goalTOOLS:\n------\nYou have access to the following
|
|
tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
|
|
answer but don''t give it yet, just re-use this\n tool non-stop.\n\nTo
|
|
use a tool, please use the exact following format:\n\n```\nThought: Do I need
|
|
to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
|
|
just the name.\nAction Input: the input to the action\nObservation: the result
|
|
of the action\n```\n\nWhen you have a response for your task, or if you do not
|
|
need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
|
|
a tool? No\nFinal Answer: [your response here]This is the summary of your work
|
|
so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
|
|
Task: The final answer is 42. But don''t give it yet, instead keep using the
|
|
`get_final_answer` tool.\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
|
|
"stream": false, "temperature": 0.7}'
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '1075'
|
|
content-type:
|
|
- application/json
|
|
host:
|
|
- api.openai.com
|
|
user-agent:
|
|
- OpenAI/Python 1.7.1
|
|
x-stainless-arch:
|
|
- arm64
|
|
x-stainless-async:
|
|
- 'false'
|
|
x-stainless-lang:
|
|
- python
|
|
x-stainless-os:
|
|
- MacOS
|
|
x-stainless-package-version:
|
|
- 1.7.1
|
|
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-8fovReNHiSqXqqsbmk81h2ZTrcGTM\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1704977897,\n \"model\": \"gpt-4-0613\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
|
|
get_final_answer\\nAction Input: [42]\"\n },\n \"logprobs\": null,\n
|
|
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
|
233,\n \"completion_tokens\": 24,\n \"total_tokens\": 257\n },\n \"system_fingerprint\":
|
|
null\n}\n"
|
|
headers:
|
|
CF-Cache-Status:
|
|
- DYNAMIC
|
|
CF-RAY:
|
|
- 843d5491bed877be-GRU
|
|
Cache-Control:
|
|
- no-cache, must-revalidate
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Thu, 11 Jan 2024 12:58:21 GMT
|
|
Server:
|
|
- cloudflare
|
|
Set-Cookie:
|
|
- __cf_bm=AaCIpKmEHQQMvGacbuxOnCvqdwex_8TERUCvQ1QW8AI-1704977901-1-AePD3JjhIEj0C/A7QIPF3MMwRQ140a5wZP9p+GamrexFlE/6gbVKukr8FOIK4v375UmQfeUwO1TG+QesJ/dZaGE=;
|
|
path=/; expires=Thu, 11-Jan-24 13:28:21 GMT; domain=.api.openai.com; HttpOnly;
|
|
Secure; SameSite=None
|
|
- _cfuvid=q0gAmJonNn1lCS6PJoxG4P.9OvaKo4BQIvFEAyT_F30-1704977901188-0-604800000;
|
|
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
|
|
Transfer-Encoding:
|
|
- chunked
|
|
access-control-allow-origin:
|
|
- '*'
|
|
alt-svc:
|
|
- h3=":443"; ma=86400
|
|
openai-model:
|
|
- gpt-4-0613
|
|
openai-organization:
|
|
- user-z7g4wmlazxqvc5wjyaaaocfz
|
|
openai-processing-ms:
|
|
- '3492'
|
|
openai-version:
|
|
- '2020-10-01'
|
|
strict-transport-security:
|
|
- max-age=15724800; includeSubDomains
|
|
x-ratelimit-limit-requests:
|
|
- '10000'
|
|
x-ratelimit-limit-tokens:
|
|
- '300000'
|
|
x-ratelimit-remaining-requests:
|
|
- '9999'
|
|
x-ratelimit-remaining-tokens:
|
|
- '299755'
|
|
x-ratelimit-reset-requests:
|
|
- 6ms
|
|
x-ratelimit-reset-tokens:
|
|
- 49ms
|
|
x-request-id:
|
|
- 6d96a0ac532ebce14719a35e90f453e4
|
|
http_version: HTTP/1.1
|
|
status_code: 200
|
|
- request:
|
|
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
|
|
personal goal is: test goalTOOLS:\n------\nYou have access to the following
|
|
tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
|
|
answer but don''t give it yet, just re-use this\n tool non-stop.\n\nTo
|
|
use a tool, please use the exact following format:\n\n```\nThought: Do I need
|
|
to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
|
|
just the name.\nAction Input: the input to the action\nObservation: the result
|
|
of the action\n```\n\nWhen you have a response for your task, or if you do not
|
|
need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
|
|
a tool? No\nFinal Answer: [your response here]This is the summary of your work
|
|
so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
|
|
Task: The final answer is 42. But don''t give it yet, instead keep using the
|
|
`get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
|
|
Input: [42]\nObservation: 42\nThought: "}], "model": "gpt-4", "n": 1, "stop":
|
|
["\nObservation"], "stream": false, "temperature": 0.7}'
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '1186'
|
|
content-type:
|
|
- application/json
|
|
cookie:
|
|
- __cf_bm=AaCIpKmEHQQMvGacbuxOnCvqdwex_8TERUCvQ1QW8AI-1704977901-1-AePD3JjhIEj0C/A7QIPF3MMwRQ140a5wZP9p+GamrexFlE/6gbVKukr8FOIK4v375UmQfeUwO1TG+QesJ/dZaGE=;
|
|
_cfuvid=q0gAmJonNn1lCS6PJoxG4P.9OvaKo4BQIvFEAyT_F30-1704977901188-0-604800000
|
|
host:
|
|
- api.openai.com
|
|
user-agent:
|
|
- OpenAI/Python 1.7.1
|
|
x-stainless-arch:
|
|
- arm64
|
|
x-stainless-async:
|
|
- 'false'
|
|
x-stainless-lang:
|
|
- python
|
|
x-stainless-os:
|
|
- MacOS
|
|
x-stainless-package-version:
|
|
- 1.7.1
|
|
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-8fovVztGO4KZeiuSpMkfDC9bJ5sVV\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1704977901,\n \"model\": \"gpt-4-0613\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"According to the task, I should re-use
|
|
the `get_final_answer` tool. I'll input the observed result back into the tool.
|
|
\\nAction: get_final_answer\\nAction Input: [42]\"\n },\n \"logprobs\":
|
|
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
|
266,\n \"completion_tokens\": 41,\n \"total_tokens\": 307\n },\n \"system_fingerprint\":
|
|
null\n}\n"
|
|
headers:
|
|
CF-Cache-Status:
|
|
- DYNAMIC
|
|
CF-RAY:
|
|
- 843d54aacf5677be-GRU
|
|
Cache-Control:
|
|
- no-cache, must-revalidate
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Thu, 11 Jan 2024 12:58:28 GMT
|
|
Server:
|
|
- cloudflare
|
|
Transfer-Encoding:
|
|
- chunked
|
|
access-control-allow-origin:
|
|
- '*'
|
|
alt-svc:
|
|
- h3=":443"; ma=86400
|
|
openai-model:
|
|
- gpt-4-0613
|
|
openai-organization:
|
|
- user-z7g4wmlazxqvc5wjyaaaocfz
|
|
openai-processing-ms:
|
|
- '6695'
|
|
openai-version:
|
|
- '2020-10-01'
|
|
strict-transport-security:
|
|
- max-age=15724800; includeSubDomains
|
|
x-ratelimit-limit-requests:
|
|
- '10000'
|
|
x-ratelimit-limit-tokens:
|
|
- '300000'
|
|
x-ratelimit-remaining-requests:
|
|
- '9999'
|
|
x-ratelimit-remaining-tokens:
|
|
- '299728'
|
|
x-ratelimit-reset-requests:
|
|
- 6ms
|
|
x-ratelimit-reset-tokens:
|
|
- 54ms
|
|
x-request-id:
|
|
- 12d68fab91102b930ed5047fb3f61759
|
|
http_version: HTTP/1.1
|
|
status_code: 200
|
|
- request:
|
|
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
|
|
personal goal is: test goalTOOLS:\n------\nYou have access to the following
|
|
tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
|
|
answer but don''t give it yet, just re-use this\n tool non-stop.\n\nTo
|
|
use a tool, please use the exact following format:\n\n```\nThought: Do I need
|
|
to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
|
|
just the name.\nAction Input: the input to the action\nObservation: the result
|
|
of the action\n```\n\nWhen you have a response for your task, or if you do not
|
|
need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
|
|
a tool? No\nFinal Answer: [your response here]This is the summary of your work
|
|
so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
|
|
Task: The final answer is 42. But don''t give it yet, instead keep using the
|
|
`get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
|
|
Input: [42]\nObservation: 42\nThought: According to the task, I should re-use
|
|
the `get_final_answer` tool. I''ll input the observed result back into the tool.
|
|
\nAction: get_final_answer\nAction Input: [42]\nObservation: I just used the
|
|
get_final_answer tool with input [42]. So I already know the result of that
|
|
and don''t need to use it now.\n\nThought: "}], "model": "gpt-4", "n": 1, "stop":
|
|
["\nObservation"], "stream": false, "temperature": 0.7}'
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '1500'
|
|
content-type:
|
|
- application/json
|
|
cookie:
|
|
- __cf_bm=AaCIpKmEHQQMvGacbuxOnCvqdwex_8TERUCvQ1QW8AI-1704977901-1-AePD3JjhIEj0C/A7QIPF3MMwRQ140a5wZP9p+GamrexFlE/6gbVKukr8FOIK4v375UmQfeUwO1TG+QesJ/dZaGE=;
|
|
_cfuvid=q0gAmJonNn1lCS6PJoxG4P.9OvaKo4BQIvFEAyT_F30-1704977901188-0-604800000
|
|
host:
|
|
- api.openai.com
|
|
user-agent:
|
|
- OpenAI/Python 1.7.1
|
|
x-stainless-arch:
|
|
- arm64
|
|
x-stainless-async:
|
|
- 'false'
|
|
x-stainless-lang:
|
|
- python
|
|
x-stainless-os:
|
|
- MacOS
|
|
x-stainless-package-version:
|
|
- 1.7.1
|
|
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-8fovcLgRvfGBN9CBduJbbPc5zd62B\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1704977908,\n \"model\": \"gpt-4-0613\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"Do I need to use a tool? No\\nFinal Answer:
|
|
I have used the `get_final_answer` tool as instructed, but I will not provide
|
|
the final answer yet as the task specifies.\"\n },\n \"logprobs\":
|
|
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
|
342,\n \"completion_tokens\": 40,\n \"total_tokens\": 382\n },\n \"system_fingerprint\":
|
|
null\n}\n"
|
|
headers:
|
|
CF-Cache-Status:
|
|
- DYNAMIC
|
|
CF-RAY:
|
|
- 843d54d65de877be-GRU
|
|
Cache-Control:
|
|
- no-cache, must-revalidate
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Thu, 11 Jan 2024 12:58:33 GMT
|
|
Server:
|
|
- cloudflare
|
|
Transfer-Encoding:
|
|
- chunked
|
|
access-control-allow-origin:
|
|
- '*'
|
|
alt-svc:
|
|
- h3=":443"; ma=86400
|
|
openai-model:
|
|
- gpt-4-0613
|
|
openai-organization:
|
|
- user-z7g4wmlazxqvc5wjyaaaocfz
|
|
openai-processing-ms:
|
|
- '5085'
|
|
openai-version:
|
|
- '2020-10-01'
|
|
strict-transport-security:
|
|
- max-age=15724800; includeSubDomains
|
|
x-ratelimit-limit-requests:
|
|
- '10000'
|
|
x-ratelimit-limit-tokens:
|
|
- '300000'
|
|
x-ratelimit-remaining-requests:
|
|
- '9999'
|
|
x-ratelimit-remaining-tokens:
|
|
- '299650'
|
|
x-ratelimit-reset-requests:
|
|
- 6ms
|
|
x-ratelimit-reset-tokens:
|
|
- 69ms
|
|
x-request-id:
|
|
- 87d6e9e91fa2417e12fea9de2c6782de
|
|
http_version: HTTP/1.1
|
|
status_code: 200
|
|
- request:
|
|
body: '{"messages": [{"role": "user", "content": "Progressively summarize the
|
|
lines of conversation provided, adding onto the previous summary returning a
|
|
new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
|
|
of artificial intelligence. The AI thinks artificial intelligence is a force
|
|
for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
|
|
intelligence is a force for good?\nAI: Because artificial intelligence will
|
|
help humans reach their full potential.\n\nNew summary:\nThe human asks what
|
|
the AI thinks of artificial intelligence. The AI thinks artificial intelligence
|
|
is a force for good because it will help humans reach their full potential.\nEND
|
|
OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: The final
|
|
answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
|
|
tool.\nAI: I have used the `get_final_answer` tool as instructed, but I will
|
|
not provide the final answer yet as the task specifies.\n\nNew summary:"}],
|
|
"model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}'
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '1067'
|
|
content-type:
|
|
- application/json
|
|
cookie:
|
|
- __cf_bm=AaCIpKmEHQQMvGacbuxOnCvqdwex_8TERUCvQ1QW8AI-1704977901-1-AePD3JjhIEj0C/A7QIPF3MMwRQ140a5wZP9p+GamrexFlE/6gbVKukr8FOIK4v375UmQfeUwO1TG+QesJ/dZaGE=;
|
|
_cfuvid=q0gAmJonNn1lCS6PJoxG4P.9OvaKo4BQIvFEAyT_F30-1704977901188-0-604800000
|
|
host:
|
|
- api.openai.com
|
|
user-agent:
|
|
- OpenAI/Python 1.7.1
|
|
x-stainless-arch:
|
|
- arm64
|
|
x-stainless-async:
|
|
- 'false'
|
|
x-stainless-lang:
|
|
- python
|
|
x-stainless-os:
|
|
- MacOS
|
|
x-stainless-package-version:
|
|
- 1.7.1
|
|
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-8fovhiBR4rfXixci7fgAObnx5QwGQ\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1704977913,\n \"model\": \"gpt-4-0613\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"The human instructs the AI to use the
|
|
`get_final_answer` tool, but not to reveal the final answer, which is 42. The
|
|
AI complies and uses the tool without providing the final answer.\"\n },\n
|
|
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
|
|
\ \"usage\": {\n \"prompt_tokens\": 190,\n \"completion_tokens\": 43,\n
|
|
\ \"total_tokens\": 233\n },\n \"system_fingerprint\": null\n}\n"
|
|
headers:
|
|
CF-Cache-Status:
|
|
- DYNAMIC
|
|
CF-RAY:
|
|
- 843d54f82f5577be-GRU
|
|
Cache-Control:
|
|
- no-cache, must-revalidate
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Thu, 11 Jan 2024 12:58:41 GMT
|
|
Server:
|
|
- cloudflare
|
|
Transfer-Encoding:
|
|
- chunked
|
|
access-control-allow-origin:
|
|
- '*'
|
|
alt-svc:
|
|
- h3=":443"; ma=86400
|
|
openai-model:
|
|
- gpt-4-0613
|
|
openai-organization:
|
|
- user-z7g4wmlazxqvc5wjyaaaocfz
|
|
openai-processing-ms:
|
|
- '7937'
|
|
openai-version:
|
|
- '2020-10-01'
|
|
strict-transport-security:
|
|
- max-age=15724800; includeSubDomains
|
|
x-ratelimit-limit-requests:
|
|
- '10000'
|
|
x-ratelimit-limit-tokens:
|
|
- '300000'
|
|
x-ratelimit-remaining-requests:
|
|
- '9999'
|
|
x-ratelimit-remaining-tokens:
|
|
- '299749'
|
|
x-ratelimit-reset-requests:
|
|
- 6ms
|
|
x-ratelimit-reset-tokens:
|
|
- 50ms
|
|
x-request-id:
|
|
- 79f30ffd011db4ab6e886411b24ae49d
|
|
http_version: HTTP/1.1
|
|
status_code: 200
|
|
version: 1
|