andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-08 15:48:29 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity
Files
9a210afd802ea9e268a1ff908fd02abf6c2c8c50
crewAI/tests/cassettes/test_cache_hitting_between_agents.yaml
João Moura 6b054651a7 Refactoring task cache to be a tool (#50) 
* Refactoring task cache to be a tool

The previous implementation of the task caching system was early exiting
the agent executor due to the fact it was returning an AgentFinish object.

This now refactors it to use a cache specific tool that is dynamically
added and forced into the agent in case of a task execution that was
already executed with the same input.
2024-01-04 21:29:42 -03:00

1466 lines
57 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```This is the summary of your work so far:\nBegin! This
is VERY important to you, your job depends on it!\n\nCurrent Task: What is 2
tims 6? Return only the number.\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:
- '2225'
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-8dRVlXc53iJRMHZgEgsHLyQnTcmnQ\",\n \"object\":
\"chat.completion\",\n \"created\": 1704411237,\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\": 486,\n \"completion_tokens\":
23,\n \"total_tokens\": 509\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 84074a19fb05520a-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 04 Jan 2024 23:34:00 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=bcWayhcE4HMKJ0X171sVkGS4gNAbmQXTWiFDSgtCOFU-1704411240-1-AbKS0gip7neWlChe/4UgontGRRzbM+PF2QzntHPKF6nY81RYM50r7TvF9tjB3zMkY3CeXsigR+C0kTjYVFjqLFo=;
path=/; expires=Fri, 05-Jan-24 00:04:00 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=aGdz584dF_HY1sdQ_zF4nkf.g9NF2CjckoJVlPoc.Fc-1704411240001-0-604800000;
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:
- '2098'
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:
- '299480'
x-ratelimit-remaining-tokens_usage_based:
- '299480'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 104ms
x-ratelimit-reset-tokens_usage_based:
- 104ms
x-request-id:
- 98c413fa0e0bc84e3d468546e3cd2f2f
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```This is the summary of your work so far:\nBegin! This
is VERY important to you, your job depends on it!\n\nCurrent Task: What is 2
tims 6? Return only the number.\nThought: Do I need to use a tool? Yes\nAction:
multiplier\nAction Input: 2,6\nObservation: 12\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:
- '2329'
content-type:
- application/json
cookie:
- _cfuvid=aGdz584dF_HY1sdQ_zF4nkf.g9NF2CjckoJVlPoc.Fc-1704411240001-0-604800000;
__cf_bm=bcWayhcE4HMKJ0X171sVkGS4gNAbmQXTWiFDSgtCOFU-1704411240-1-AbKS0gip7neWlChe/4UgontGRRzbM+PF2QzntHPKF6nY81RYM50r7TvF9tjB3zMkY3CeXsigR+C0kTjYVFjqLFo=
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-8dRVoc5CcZPD8nFzRBy2gFPp8ve6v\",\n \"object\":
\"chat.completion\",\n \"created\": 1704411240,\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:
12\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 519,\n \"completion_tokens\":
15,\n \"total_tokens\": 534\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 84074a2afdf6520a-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 04 Jan 2024 23:34:02 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:
- '2037'
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:
- '299455'
x-ratelimit-remaining-tokens_usage_based:
- '299455'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 109ms
x-ratelimit-reset-tokens_usage_based:
- 109ms
x-request-id:
- d870981f801ad59b592bfd906aa59732
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? Return only the number.\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:
- '895'
content-type:
- application/json
cookie:
- _cfuvid=aGdz584dF_HY1sdQ_zF4nkf.g9NF2CjckoJVlPoc.Fc-1704411240001-0-604800000;
__cf_bm=bcWayhcE4HMKJ0X171sVkGS4gNAbmQXTWiFDSgtCOFU-1704411240-1-AbKS0gip7neWlChe/4UgontGRRzbM+PF2QzntHPKF6nY81RYM50r7TvF9tjB3zMkY3CeXsigR+C0kTjYVFjqLFo=
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-8dRVqwa7QwjlYpBCg5xaUZEWTIMoe\",\n \"object\":
\"chat.completion\",\n \"created\": 1704411242,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The human asks the AI to calculate 2
times 6, and the AI responds with the answer, 12.\"\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
155,\n \"completion_tokens\": 24,\n \"total_tokens\": 179\n },\n \"system_fingerprint\":
null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 84074a3aee55520a-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 04 Jan 2024 23:34:04 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:
- '1160'
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:
- '299791'
x-ratelimit-remaining-tokens_usage_based:
- '299791'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 41ms
x-ratelimit-reset-tokens_usage_based:
- 41ms
x-request-id:
- f5f275f8bbce5e3a96781845bea91b8c
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```This is the summary of your work so far:\nBegin! This
is VERY important to you, your job depends on it!\n\nCurrent Task: What is 2
times 6? Return only the number.\n\nThis is the context you are working with:\n12\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:
- '1514'
content-type:
- application/json
cookie:
- _cfuvid=BMxGwK4wPoN6Cq5150swBY7QbtTvmWU2.p39x.cUidg-1703932144438-0-604800000
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-8dRVst73yaZUVvqi8MkAdhYgxy8Yp\",\n \"object\":
\"chat.completion\",\n \"created\": 1704411244,\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\": 318,\n \"completion_tokens\":
23,\n \"total_tokens\": 341\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 84074a4539a1a4dd-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 04 Jan 2024 23:34:06 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=OBFg78fHa0ijnfAz8h6GymXWDgMj3jeHXBT3OmSgjnY-1704411246-1-AWv0YbE4Eky1dIJX16Gtn4yWnbpu0r+Jn1JKPJgjtWT/r8Q4SPDBV2cO8dro6v3MkATOZxXk4/Wcy3m7XL5s9Zk=;
path=/; expires=Fri, 05-Jan-24 00:04:06 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=mmDWVPda72fr6EU7NUfzAtK5KCOZi4RsQOabwHXVa98-1704411246977-0-604800000;
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:
- '2183'
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:
- 5e830a8376085c6ce2df403dbecb5a8f
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```This is the summary of your work so far:\nBegin! This
is VERY important to you, your job depends on it!\n\nCurrent Task: What is 2
times 6? Return only the number.\n\nThis is the context you are working with:\n12\nThought:
Do I need to use a tool? Yes\nAction: multiplier\nAction Input: 2,6\nObservation:
12\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:
- '1618'
content-type:
- application/json
cookie:
- _cfuvid=mmDWVPda72fr6EU7NUfzAtK5KCOZi4RsQOabwHXVa98-1704411246977-0-604800000;
__cf_bm=OBFg78fHa0ijnfAz8h6GymXWDgMj3jeHXBT3OmSgjnY-1704411246-1-AWv0YbE4Eky1dIJX16Gtn4yWnbpu0r+Jn1JKPJgjtWT/r8Q4SPDBV2cO8dro6v3MkATOZxXk4/Wcy3m7XL5s9Zk=
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-8dRVvTsWLclXQnmY67VWcdxVqY3ul\",\n \"object\":
\"chat.completion\",\n \"created\": 1704411247,\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:
12\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 351,\n \"completion_tokens\":
15,\n \"total_tokens\": 366\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 84074a55f935a4dd-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 04 Jan 2024 23:34:08 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:
- '1539'
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:
- '299621'
x-ratelimit-remaining-tokens_usage_based:
- '299621'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 75ms
x-ratelimit-reset-tokens_usage_based:
- 75ms
x-request-id:
- bdbe02bf0b83c88f824c067b27e5ce08
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? Return only the number.\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:
- '945'
content-type:
- application/json
cookie:
- _cfuvid=mmDWVPda72fr6EU7NUfzAtK5KCOZi4RsQOabwHXVa98-1704411246977-0-604800000;
__cf_bm=OBFg78fHa0ijnfAz8h6GymXWDgMj3jeHXBT3OmSgjnY-1704411246-1-AWv0YbE4Eky1dIJX16Gtn4yWnbpu0r+Jn1JKPJgjtWT/r8Q4SPDBV2cO8dro6v3MkATOZxXk4/Wcy3m7XL5s9Zk=
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-8dRVxzDne3c08p3cTarxVS8coZYTY\",\n \"object\":
\"chat.completion\",\n \"created\": 1704411249,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The human asks the AI to calculate 2
times 6, and the AI responds with the correct answer, 12.\"\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
165,\n \"completion_tokens\": 25,\n \"total_tokens\": 190\n },\n \"system_fingerprint\":
null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 84074a610867a4dd-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 04 Jan 2024 23:34:12 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:
- '2856'
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:
- '299780'
x-ratelimit-remaining-tokens_usage_based:
- '299780'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 44ms
x-ratelimit-reset-tokens_usage_based:
- 44ms
x-request-id:
- bc1098a0a70b65dd693837175bdd9c7a
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```This is
the summary of your work so far:\nThe human asks the AI to calculate 2 times
6, and the AI responds with the answer, 12.Begin! This is VERY important to
you, your job depends on it!\n\nCurrent Task: What is 2 tims 6? Return only
the number.\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:
- '3098'
content-type:
- application/json
cookie:
- _cfuvid=aGdz584dF_HY1sdQ_zF4nkf.g9NF2CjckoJVlPoc.Fc-1704411240001-0-604800000;
__cf_bm=bcWayhcE4HMKJ0X171sVkGS4gNAbmQXTWiFDSgtCOFU-1704411240-1-AbKS0gip7neWlChe/4UgontGRRzbM+PF2QzntHPKF6nY81RYM50r7TvF9tjB3zMkY3CeXsigR+C0kTjYVFjqLFo=
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-8dRW0twTa8zcVszzkf4rHaJtBQyuE\",\n \"object\":
\"chat.completion\",\n \"created\": 1704411252,\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:
- 84074a768894016c-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 04 Jan 2024 23:34:13 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:
- '1169'
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:
- '299272'
x-ratelimit-remaining-tokens_usage_based:
- '299272'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 145ms
x-ratelimit-reset-tokens_usage_based:
- 145ms
x-request-id:
- b486103e6e3ed65ba15411a1fcd1534a
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```This is
the summary of your work so far:\nThe human asks the AI to calculate 2 times
6, and the AI responds with the answer, 12.Begin! This is VERY important to
you, your job depends on it!\n\nCurrent Task: What is 2 tims 6? Return only
the number.\n\nI just used the multiplier tool with input 2,6. So I already
know the result of that.\nObservation: Invalid or incomplete response\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:
- '3241'
content-type:
- application/json
cookie:
- _cfuvid=aGdz584dF_HY1sdQ_zF4nkf.g9NF2CjckoJVlPoc.Fc-1704411240001-0-604800000;
__cf_bm=bcWayhcE4HMKJ0X171sVkGS4gNAbmQXTWiFDSgtCOFU-1704411240-1-AbKS0gip7neWlChe/4UgontGRRzbM+PF2QzntHPKF6nY81RYM50r7TvF9tjB3zMkY3CeXsigR+C0kTjYVFjqLFo=
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-8dRW1CmfWI2T4pqcjA32JkFO2d631\",\n \"object\":
\"chat.completion\",\n \"created\": 1704411253,\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:
12\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 721,\n \"completion_tokens\":
15,\n \"total_tokens\": 736\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 84074a801ca8016c-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 04 Jan 2024 23:34:15 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:
- '1961'
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:
- '299236'
x-ratelimit-remaining-tokens_usage_based:
- '299236'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 152ms
x-ratelimit-reset-tokens_usage_based:
- 152ms
x-request-id:
- 555ce73ac9d4daed7f521005a3d040e0
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 to calculate 2 times 6,
and the AI responds with the answer, 12.\n\nNew lines of conversation:\nHuman:
What is 2 tims 6? Return only the number.\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:
- '981'
content-type:
- application/json
cookie:
- _cfuvid=aGdz584dF_HY1sdQ_zF4nkf.g9NF2CjckoJVlPoc.Fc-1704411240001-0-604800000;
__cf_bm=bcWayhcE4HMKJ0X171sVkGS4gNAbmQXTWiFDSgtCOFU-1704411240-1-AbKS0gip7neWlChe/4UgontGRRzbM+PF2QzntHPKF6nY81RYM50r7TvF9tjB3zMkY3CeXsigR+C0kTjYVFjqLFo=
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-8dRW49WMzFv360XBT2uhgJPnSHg2O\",\n \"object\":
\"chat.completion\",\n \"created\": 1704411256,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The human asks the AI to calculate 2
times 6 twice, and both times the AI correctly responds with the answer, 12.\"\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 179,\n \"completion_tokens\":
28,\n \"total_tokens\": 207\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 84074a8dfccf016c-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 04 Jan 2024 23:34:18 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:
- '2192'
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:
- '299770'
x-ratelimit-remaining-tokens_usage_based:
- '299770'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 46ms
x-ratelimit-reset-tokens_usage_based:
- 46ms
x-request-id:
- f5dda6e21a06ac9af1a14b27c551c3c1
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```This is the summary of your work so far:\nThe human
asks the AI to calculate 2 times 6, and the AI responds with the correct answer,
12.Begin! This is VERY important to you, your job depends on it!\n\nCurrent
Task: What is 2 times 6? Return only the number.\n\nThis is the context you
are working with:\n12\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:
- '1608'
content-type:
- application/json
cookie:
- _cfuvid=mmDWVPda72fr6EU7NUfzAtK5KCOZi4RsQOabwHXVa98-1704411246977-0-604800000;
__cf_bm=OBFg78fHa0ijnfAz8h6GymXWDgMj3jeHXBT3OmSgjnY-1704411246-1-AWv0YbE4Eky1dIJX16Gtn4yWnbpu0r+Jn1JKPJgjtWT/r8Q4SPDBV2cO8dro6v3MkATOZxXk4/Wcy3m7XL5s9Zk=
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-8dRW6CHiFSw6vFRNx1T4uAmrAW8dK\",\n \"object\":
\"chat.completion\",\n \"created\": 1704411258,\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\": 342,\n \"completion_tokens\":
23,\n \"total_tokens\": 365\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 84074a9ddedf01c1-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 04 Jan 2024 23:34:19 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:
- '1023'
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:
- '299624'
x-ratelimit-remaining-tokens_usage_based:
- '299624'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 75ms
x-ratelimit-reset-tokens_usage_based:
- 75ms
x-request-id:
- f28da711e3c1ff3e058def7cf176f30a
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```This is the summary of your work so far:\nThe human
asks the AI to calculate 2 times 6, and the AI responds with the correct answer,
12.Begin! This is VERY important to you, your job depends on it!\n\nCurrent
Task: What is 2 times 6? Return only the number.\n\nThis is the context you
are working with:\n12\nThought: Do I need to use a tool? Yes\nAction: multiplier\nAction
Input: 2,6\nObservation: 12\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:
- '1712'
content-type:
- application/json
cookie:
- _cfuvid=mmDWVPda72fr6EU7NUfzAtK5KCOZi4RsQOabwHXVa98-1704411246977-0-604800000;
__cf_bm=OBFg78fHa0ijnfAz8h6GymXWDgMj3jeHXBT3OmSgjnY-1704411246-1-AWv0YbE4Eky1dIJX16Gtn4yWnbpu0r+Jn1JKPJgjtWT/r8Q4SPDBV2cO8dro6v3MkATOZxXk4/Wcy3m7XL5s9Zk=
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-8dRW7NNdda8hGNJVbrkPRDzPdO7dZ\",\n \"object\":
\"chat.completion\",\n \"created\": 1704411259,\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:
12\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 375,\n \"completion_tokens\":
15,\n \"total_tokens\": 390\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 84074aa5fb2e01c1-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 04 Jan 2024 23:34:21 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:
- '1280'
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:
- '299599'
x-ratelimit-remaining-tokens_usage_based:
- '299599'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 80ms
x-ratelimit-reset-tokens_usage_based:
- 80ms
x-request-id:
- 888c0944f22db01f2ac38963b94c765d
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 to calculate 2 times 6,
and the AI responds with the correct answer, 12.\n\nNew lines of conversation:\nHuman:
What is 2 times 6? Return only the number.\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:
- '1039'
content-type:
- application/json
cookie:
- _cfuvid=mmDWVPda72fr6EU7NUfzAtK5KCOZi4RsQOabwHXVa98-1704411246977-0-604800000;
__cf_bm=OBFg78fHa0ijnfAz8h6GymXWDgMj3jeHXBT3OmSgjnY-1704411246-1-AWv0YbE4Eky1dIJX16Gtn4yWnbpu0r+Jn1JKPJgjtWT/r8Q4SPDBV2cO8dro6v3MkATOZxXk4/Wcy3m7XL5s9Zk=
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-8dRW9lh9rXOLN3eN1fhXjtc7JnCX8\",\n \"object\":
\"chat.completion\",\n \"created\": 1704411261,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The human asks the AI to calculate 2
times 6 twice, and both times the AI responds with the correct answer, 12.\"\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 190,\n \"completion_tokens\":
28,\n \"total_tokens\": 218\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 84074aaf99a001c1-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 04 Jan 2024 23:34:24 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:
- '2998'
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:
- '299755'
x-ratelimit-remaining-tokens_usage_based:
- '299755'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 48ms
x-ratelimit-reset-tokens_usage_based:
- 48ms
x-request-id:
- 9cbb02f45069e8274ca90e4ee7e690db
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink