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 3 Packages Projects Releases Wiki Activity
Files
af9e749edb1100b56cfbd44347ac7560ab0abc64
crewAI/tests/cassettes/test_cache_hitting_between_agents.yaml
João Moura af9e749edb Adding tool caching a loop execution prevention. (#25) 
* Adding tool caching a loop execution prevention.

This adds some guardrails, to both prevent the same tool to be used
consecutively and also caching tool's results across the entire crew
so it cuts down execution time and eventual LLM calls.

This plays a huge role for smaller opensource models that usually fall
into those behaviors patterns.

It also includes some smaller improvements around the tool prompt and
agent tools, all with the same intention of guiding models into
better conform with agent instructions.
2023-12-29 22:35:23 -03:00

1085 lines
42 KiB
YAML
Raw Blame History

interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are CEO.\nYou''re an long
time CEO of a content creation agency with a Senior Writer on the team. You''re
now working on a new project and want to make sure the content produced is amazing.\n\nYour
personal goal is: Make sure the writers in your company produce amazing content.\n\nTOOLS:\n------\nYou
have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float
- Useful for when you need to multiply two numbers together.\n The input
to this tool should be a comma separated list of numbers of\n length
two, representing the two numbers you want to multiply together.\n For
example, `1,2` would be the input if you wanted to multiply 1 by 2.\nDelegate
work to co-worker: Useful to delegate a specific task to one of the\n\t\t\t\tfollowing
co-workers: [CEO, Researcher].\n\t\t\t\tThe input to this tool should be a pipe
(|) separated text of length\n\t\t\t\tthree, representing the role you want
to delegate it to, the task and\n\t\t\t\tinformation necessary. For example,
`coworker|task|information`.\n\nAsk question to co-worker: Useful to ask a question,
opinion or take from on\n\t\t\t\tof the following co-workers: [CEO, Researcher].\n\t\t\t\tThe
input to this tool should be a pipe (|) separated text of length\n\t\t\t\tthree,
representing the role you want to ask it to, the question and\n\t\t\t\tinformation
necessary. For example, `coworker|question|information`.\n\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 [multiplier, Delegate work
to co-worker, Ask question to co-worker], 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]\n```\n\t\tThis is the summary of your work so far:\n \nBegin!
This is VERY important to you, your job depends on it!\n\nCurrent Task: What
is 2 tims 6?\n\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:
- '2215'
content-type:
- application/json
cookie:
- _cfuvid=ps.JYe.5DT5QaG1hDuUb70tnVJo8IPWJrGrGEO_HUYA-1703099776177-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
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-8bFlFR80bKQQzwjFzAICpcBT2G3s0\",\n \"object\":
\"chat.completion\",\n \"created\": 1703889413,\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:
multiplier\\nAction Input: 2,6\\n\"\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 484,\n \"completion_tokens\":
24,\n \"total_tokens\": 508\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d5863e9a050301-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 22:36:54 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=6RpGZVaY4yiI4M4AoreJuJny2199LZXRkp8DDrcSK5k-1703889414-1-AdxFp5oHDyE1t+/uGSC6LyRh7n4+ats5oznbOnwXmT+G4BkBdSY9kVWLS2RSLndYHxVzz5ksSBcREfL/gr1HAAc=;
path=/; expires=Fri, 29-Dec-23 23:06:54 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=O8jSUEuY34NDEdF4z_HQGq8w7idZ7PZlcpp1vRj2y5E-1703889414566-0-604800000;
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:
- '1227'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299483'
x-ratelimit-remaining-tokens_usage_based:
- '299483'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 103ms
x-ratelimit-reset-tokens_usage_based:
- 103ms
x-request-id:
- 938270aa00d199e6be67525b6e3d6eba
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are CEO.\nYou''re an long
time CEO of a content creation agency with a Senior Writer on the team. You''re
now working on a new project and want to make sure the content produced is amazing.\n\nYour
personal goal is: Make sure the writers in your company produce amazing content.\n\nTOOLS:\n------\nYou
have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float
- Useful for when you need to multiply two numbers together.\n The input
to this tool should be a comma separated list of numbers of\n length
two, representing the two numbers you want to multiply together.\n For
example, `1,2` would be the input if you wanted to multiply 1 by 2.\nDelegate
work to co-worker: Useful to delegate a specific task to one of the\n\t\t\t\tfollowing
co-workers: [CEO, Researcher].\n\t\t\t\tThe input to this tool should be a pipe
(|) separated text of length\n\t\t\t\tthree, representing the role you want
to delegate it to, the task and\n\t\t\t\tinformation necessary. For example,
`coworker|task|information`.\n\nAsk question to co-worker: Useful to ask a question,
opinion or take from on\n\t\t\t\tof the following co-workers: [CEO, Researcher].\n\t\t\t\tThe
input to this tool should be a pipe (|) separated text of length\n\t\t\t\tthree,
representing the role you want to ask it to, the question and\n\t\t\t\tinformation
necessary. For example, `coworker|question|information`.\n\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 [multiplier, Delegate work
to co-worker, Ask question to co-worker], 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]\n```\n\t\tThis is the summary of your work so far:\n \nBegin!
This is VERY important to you, your job depends on it!\n\nCurrent Task: What
is 2 tims 6?\nThought: Do I need to use a tool? Yes\nAction: multiplier\nAction
Input: 2,6\n\nObservation: 12\nThought: \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:
- '2321'
content-type:
- application/json
cookie:
- _cfuvid=O8jSUEuY34NDEdF4z_HQGq8w7idZ7PZlcpp1vRj2y5E-1703889414566-0-604800000;
__cf_bm=6RpGZVaY4yiI4M4AoreJuJny2199LZXRkp8DDrcSK5k-1703889414-1-AdxFp5oHDyE1t+/uGSC6LyRh7n4+ats5oznbOnwXmT+G4BkBdSY9kVWLS2RSLndYHxVzz5ksSBcREfL/gr1HAAc=
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
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-8bFlGBZrFqbUBA6wWFIW1k7CrvOMc\",\n \"object\":
\"chat.completion\",\n \"created\": 1703889414,\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:
2 times 6 is 12.\"\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 517,\n \"completion_tokens\":
22,\n \"total_tokens\": 539\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d586496c140301-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 22:36:59 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:
- '2377'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299458'
x-ratelimit-remaining-tokens_usage_based:
- '299458'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 108ms
x-ratelimit-reset-tokens_usage_based:
- 108ms
x-request-id:
- ab3bab4c142330d66869ccff39de5738
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: What
is 2 tims 6?\nAI: 2 times 6 is 12.\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:
- '885'
content-type:
- application/json
cookie:
- _cfuvid=O8jSUEuY34NDEdF4z_HQGq8w7idZ7PZlcpp1vRj2y5E-1703889414566-0-604800000;
__cf_bm=6RpGZVaY4yiI4M4AoreJuJny2199LZXRkp8DDrcSK5k-1703889414-1-AdxFp5oHDyE1t+/uGSC6LyRh7n4+ats5oznbOnwXmT+G4BkBdSY9kVWLS2RSLndYHxVzz5ksSBcREfL/gr1HAAc=
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
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-8bFlMHhxpCjHkQymfxQ5D8WBZkclA\",\n \"object\":
\"chat.completion\",\n \"created\": 1703889420,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The human asks the AI for the product
of 2 times 6, and the AI responds that it is 12.\"\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
156,\n \"completion_tokens\": 25,\n \"total_tokens\": 181\n },\n \"system_fingerprint\":
null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d5866a6c360301-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 22:37:01 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:
- '1468'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299794'
x-ratelimit-remaining-tokens_usage_based:
- '299794'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 41ms
x-ratelimit-reset-tokens_usage_based:
- 41ms
x-request-id:
- e6e04fb8a12fc2288d6a3bd0b4480ab0
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are Researcher.\nYou''re
an expert researcher, specialized in technology, software engineering, AI and
startups. You work as a freelancer and is now working on doing research and
analysis for a new customer.\n\nYour personal goal is: Make the best research
and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou have access
to the following tools:\n\nmultiplier: multiplier(numbers) -> float - Useful
for when you need to multiply two numbers together.\n The input to this
tool should be a comma separated list of numbers of\n length two, representing
the two numbers you want to multiply together.\n For example, `1,2` would
be the input if you wanted to multiply 1 by 2.\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 [multiplier], 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]\n```\n\t\tThis is the summary of your work so far:\n \nBegin!
This is VERY important to you, your job depends on it!\n\nCurrent Task: What
is 2 times 6?\n\nThis is the context you are working with:\n2 times 6 is 12.\n\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:
- '1518'
content-type:
- application/json
cookie:
- _cfuvid=u_fUK0MqnLcrbhMkg8kKMfrSZpALgzClvD984s71oU8-1703091698056-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
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-8bFlOAG2g3FwravPGs5nQmnA8wpf1\",\n \"object\":
\"chat.completion\",\n \"created\": 1703889422,\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:
multiplier\\nAction Input: 2,6\"\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 322,\n \"completion_tokens\":
23,\n \"total_tokens\": 345\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d586773aea77c0-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 22:37:04 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=NTFlpt52iEoCg0Pkx5.1jxp.b3GIrmzDorPoCjgwA1c-1703889424-1-AcnqI2v1g/4ArTSHF6F4yC9cQd8KWJUiSRlY3mTNPF+6P6fectfBIvD544RQw/zhEY+z/eZ5pw4t/Baew653jtw=;
path=/; expires=Fri, 29-Dec-23 23:07:04 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=yTJHDMg7VYHMEKTSaPhpQp_5NZ3Xw1rIS8dQw4LmQMk-1703889424692-0-604800000;
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:
- '2511'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299646'
x-ratelimit-remaining-tokens_usage_based:
- '299646'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 70ms
x-ratelimit-reset-tokens_usage_based:
- 70ms
x-request-id:
- b86341441fa500dc373240b329cf5446
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: What
is 2 times 6?\n\nThis is the context you are working with:\n2 times 6 is 12.\nAI:
12\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:
- '935'
content-type:
- application/json
cookie:
- _cfuvid=yTJHDMg7VYHMEKTSaPhpQp_5NZ3Xw1rIS8dQw4LmQMk-1703889424692-0-604800000;
__cf_bm=NTFlpt52iEoCg0Pkx5.1jxp.b3GIrmzDorPoCjgwA1c-1703889424-1-AcnqI2v1g/4ArTSHF6F4yC9cQd8KWJUiSRlY3mTNPF+6P6fectfBIvD544RQw/zhEY+z/eZ5pw4t/Baew653jtw=
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
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-8bFlQVqyX43MFLq79thTQ8UaZZ1xD\",\n \"object\":
\"chat.completion\",\n \"created\": 1703889424,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The human asks the AI what is 2 times
6, and the AI responds with 12.\"\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 166,\n \"completion_tokens\":
21,\n \"total_tokens\": 187\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d58688eda777c0-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 22:37:06 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:
- '1152'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299782'
x-ratelimit-remaining-tokens_usage_based:
- '299782'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 43ms
x-ratelimit-reset-tokens_usage_based:
- 43ms
x-request-id:
- d86894b3054720d2053d5bfef884d985
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are CEO.\nYou''re an long
time CEO of a content creation agency with a Senior Writer on the team. You''re
now working on a new project and want to make sure the content produced is amazing.\n\nYour
personal goal is: Make sure the writers in your company produce amazing content.\n\nTOOLS:\n------\nYou
have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float
- Useful for when you need to multiply two numbers together.\n The input
to this tool should be a comma separated list of numbers of\n length
two, representing the two numbers you want to multiply together.\n For
example, `1,2` would be the input if you wanted to multiply 1 by 2.\nDelegate
work to co-worker: Useful to delegate a specific task to one of the\n\t\t\t\tfollowing
co-workers: [CEO, Researcher].\n\t\t\t\tThe input to this tool should be a pipe
(|) separated text of length\n\t\t\t\tthree, representing the role you want
to delegate it to, the task and\n\t\t\t\tinformation necessary. For example,
`coworker|task|information`.\n\nAsk question to co-worker: Useful to ask a question,
opinion or take from on\n\t\t\t\tof the following co-workers: [CEO, Researcher].\n\t\t\t\tThe
input to this tool should be a pipe (|) separated text of length\n\t\t\t\tthree,
representing the role you want to ask it to, the question and\n\t\t\t\tinformation
necessary. For example, `coworker|question|information`.\n\nDelegate work to
co-worker: Useful to delegate a specific task to one of the\n\t\t\t\tfollowing
co-workers: [CEO, Researcher].\n\t\t\t\tThe input to this tool should be a pipe
(|) separated text of length\n\t\t\t\tthree, representing the role you want
to delegate it to, the task and\n\t\t\t\tinformation necessary. For example,
`coworker|task|information`.\n\nAsk question to co-worker: Useful to ask a question,
opinion or take from on\n\t\t\t\tof the following co-workers: [CEO, Researcher].\n\t\t\t\tThe
input to this tool should be a pipe (|) separated text of length\n\t\t\t\tthree,
representing the role you want to ask it to, the question and\n\t\t\t\tinformation
necessary. For example, `coworker|question|information`.\n\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 [multiplier, Delegate work
to co-worker, Ask question to co-worker, Delegate work to co-worker, Ask question
to co-worker], 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]\n```\n\t\tThis
is the summary of your work so far:\n The human asks the AI for the product
of 2 times 6, and the AI responds that it is 12.\nBegin! This is VERY important
to you, your job depends on it!\n\nCurrent Task: What is 2 tims 6?\n\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:
- '3088'
content-type:
- application/json
cookie:
- _cfuvid=O8jSUEuY34NDEdF4z_HQGq8w7idZ7PZlcpp1vRj2y5E-1703889414566-0-604800000;
__cf_bm=6RpGZVaY4yiI4M4AoreJuJny2199LZXRkp8DDrcSK5k-1703889414-1-AdxFp5oHDyE1t+/uGSC6LyRh7n4+ats5oznbOnwXmT+G4BkBdSY9kVWLS2RSLndYHxVzz5ksSBcREfL/gr1HAAc=
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
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-8bFlSjjmk16fcEx4qjS8HvNxbn3ky\",\n \"object\":
\"chat.completion\",\n \"created\": 1703889426,\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:
multiplier\\nAction Input: 2,6\"\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 688,\n \"completion_tokens\":
23,\n \"total_tokens\": 711\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d58691fc2e0301-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 22:37:07 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:
- '1307'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299275'
x-ratelimit-remaining-tokens_usage_based:
- '299275'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 144ms
x-ratelimit-reset-tokens_usage_based:
- 144ms
x-request-id:
- e25c77d8a956e2d403a80795d27446ed
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:\nThe human asks the AI for the product of 2 times
6, and the AI responds that it is 12.\n\nNew lines of conversation:\nHuman:
What is 2 tims 6?\nAI: 12\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:
- '957'
content-type:
- application/json
cookie:
- _cfuvid=O8jSUEuY34NDEdF4z_HQGq8w7idZ7PZlcpp1vRj2y5E-1703889414566-0-604800000;
__cf_bm=6RpGZVaY4yiI4M4AoreJuJny2199LZXRkp8DDrcSK5k-1703889414-1-AdxFp5oHDyE1t+/uGSC6LyRh7n4+ats5oznbOnwXmT+G4BkBdSY9kVWLS2RSLndYHxVzz5ksSBcREfL/gr1HAAc=
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
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-8bFlTYmUO6Wh3mbgtPshKpQqqDxgd\",\n \"object\":
\"chat.completion\",\n \"created\": 1703889427,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The human asks the AI for the product
of 2 times 6, and the AI responds that it is 12, confirming this when asked
again.\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 175,\n \"completion_tokens\":
31,\n \"total_tokens\": 206\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d5869baf8a0301-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 22:37:09 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:
- '1618'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299775'
x-ratelimit-remaining-tokens_usage_based:
- '299775'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 44ms
x-ratelimit-reset-tokens_usage_based:
- 44ms
x-request-id:
- b70f47e489a1fefedc547c87e41f7dae
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are Researcher.\nYou''re
an expert researcher, specialized in technology, software engineering, AI and
startups. You work as a freelancer and is now working on doing research and
analysis for a new customer.\n\nYour personal goal is: Make the best research
and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou have access
to the following tools:\n\nmultiplier: multiplier(numbers) -> float - Useful
for when you need to multiply two numbers together.\n The input to this
tool should be a comma separated list of numbers of\n length two, representing
the two numbers you want to multiply together.\n For example, `1,2` would
be the input if you wanted to multiply 1 by 2.\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 [multiplier], 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]\n```\n\t\tThis is the summary of your work so far:\n The
human asks the AI what is 2 times 6, and the AI responds with 12.\nBegin! This
is VERY important to you, your job depends on it!\n\nCurrent Task: What is 2
times 6?\n\nThis is the context you are working with:\n12\n\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:
- '1573'
content-type:
- application/json
cookie:
- _cfuvid=yTJHDMg7VYHMEKTSaPhpQp_5NZ3Xw1rIS8dQw4LmQMk-1703889424692-0-604800000;
__cf_bm=NTFlpt52iEoCg0Pkx5.1jxp.b3GIrmzDorPoCjgwA1c-1703889424-1-AcnqI2v1g/4ArTSHF6F4yC9cQd8KWJUiSRlY3mTNPF+6P6fectfBIvD544RQw/zhEY+z/eZ5pw4t/Baew653jtw=
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
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-8bFlVgnFkN5XO7X3qLOx96HX1pUjS\",\n \"object\":
\"chat.completion\",\n \"created\": 1703889429,\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:
multiplier\\nAction Input: 2,6\"\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 337,\n \"completion_tokens\":
23,\n \"total_tokens\": 360\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d586a76ee577c0-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 22:37:11 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:
- '1612'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299634'
x-ratelimit-remaining-tokens_usage_based:
- '299634'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 73ms
x-ratelimit-reset-tokens_usage_based:
- 73ms
x-request-id:
- 739f95896087931128c8e260b7d3cf02
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:\nThe human asks the AI what is 2 times 6, and
the AI responds with 12.\n\nNew lines of conversation:\nHuman: What is 2 times
6?\n\nThis is the context you are working with:\n12\nAI: 12\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:
- '990'
content-type:
- application/json
cookie:
- _cfuvid=yTJHDMg7VYHMEKTSaPhpQp_5NZ3Xw1rIS8dQw4LmQMk-1703889424692-0-604800000;
__cf_bm=NTFlpt52iEoCg0Pkx5.1jxp.b3GIrmzDorPoCjgwA1c-1703889424-1-AcnqI2v1g/4ArTSHF6F4yC9cQd8KWJUiSRlY3mTNPF+6P6fectfBIvD544RQw/zhEY+z/eZ5pw4t/Baew653jtw=
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
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-8bFlXEDmlitriA40K77evvaqJrfZ4\",\n \"object\":
\"chat.completion\",\n \"created\": 1703889431,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The human asks the AI what is 2 times
6, and the AI consistently responds with 12.\"\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
181,\n \"completion_tokens\": 22,\n \"total_tokens\": 203\n },\n \"system_fingerprint\":
null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d586b2fbd877c0-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 22:37:13 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:
- '1836'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299769'
x-ratelimit-remaining-tokens_usage_based:
- '299769'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 46ms
x-ratelimit-reset-tokens_usage_based:
- 46ms
x-request-id:
- 501523f2159a6ae7b2dbb409cf5748a1
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink