andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-10 00:28:31 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
Files
d4c21a23f4503ae7aac9de61f9794031cffb6b19
crewAI/tests/cassettes/test_cache_hitting_between_agents.yaml
João Moura d4c21a23f4 updating all cassettes
2024-02-10 00:55:40 -08:00

1918 lines
75 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.TOOLS:\n------\nYou
have access to only the following tools:\n\nmultiplier: multiplier(first_number:
int, second_number: int) -> float - Useful for when you need to multiply two
numbers together.\nDelegate work to co-worker: Delegate work to co-worker(coworker:
str, task: str, context: str) - Delegate a specific task to one of the following
co-workers: Researcher. The input to this tool should be the role of the coworker,
the task you want them to do, and ALL necessary context to exectue the task,
they know nothing about the task, so share absolute everything you know, don''t
reference things but instead explain them.\nAsk question to co-worker: Ask question
to co-worker(coworker: str, question: str, context: str) - Ask a specific question
to one of the following co-workers: Researcher. The input to this tool should
be the role of the coworker, the question you have for them, and ALL necessary
context to ask the question properly, they know nothing about the question,
so share absolute everything you know, don''t reference things but instead explain
them.\n\nTo use a tool, please use the exact following format:\n\n```\nThought:
Do I need to use a tool? Yes\nAction: the tool you wanna use, should be one
of [multiplier, Delegate work to co-worker, Ask question to co-worker], just
the name.\nAction Input: Any and all relevant information input and context
for using the tool\nObservation: the result of using the tool\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: 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:
- '2209'
content-type:
- application/json
cookie:
- _cfuvid=ps.JYe.5DT5QaG1hDuUb70tnVJo8IPWJrGrGEO_HUYA-1703099776177-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.12.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.12.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SRS0/DMBCE7/kVqz23qKWPQC4IFYQqIbj0AKKoSp1tYrC9xt5IoKr/HTl9wcWH
Gc/oG3ubAaCusABUTSnKetO/+qqen/P49PA1fzTDxe39yM3yRWNn/PIywl5K8PqDlBxTF4qtNySa
3d5WgUqh1DrMB/lkMhnml51huSKTYrWX/rg/mA4PhaphrShiAW8ZAMC2OxObq+gbCxj0joqlGMua
sDhdAsDAJilYxqijlE6wdzYVOyHX4S4abutGCrhjmIMjqkAY2khQgjCbG3iluHS3Ko0pwLZGtDea
wlGDufOtFLBd4kaHKCvX2jWFJRZw2YMlRlLsqj/qdIcHkt1pguHaB16nua415qRvtNOxWQUqI7uE
G4X9Pr7LAN67p2r/rUcf2HpZCX+SS4XjfLrvw/OvnN3R6GAKS2nO+mRwnR0IMf5EIbvaaFdT8EF3
L5c4s132CwAA//8DAM/4gzMwAgAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 85331e527a1f9e6b-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 08:52:54 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=tE85KSJVLW2b9uFQ3HdC_0X9zKb3zvxn_XQrw65Lr5I-1707555174-1-ASbOkyjQPFYaEjdVU9A62Rq43RljO+iw67jesVCWW1SR/PnNWomyDmLymjV9qhbKx0TBnRfqMk7Mva8JQd1CH8A=;
path=/; expires=Sat, 10-Feb-24 09:22:54 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=5kZVxJOsRfxObr9hLdehia3eWTY.wvyv.6QajmkP_hU-1707555174271-0-604800000;
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:
- '1951'
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:
- '299471'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 105ms
x-request-id:
- req_840a3e56830b72446f213b26b89c5603
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "Return a valid schema for the
one tool you must use with its arguments and values.\n\nTools available:\n\nFuntion
Name: multiplier\nFuntion attributes: {''first_number'': {''type'': ''integer''},
''second_number'': {''type'': ''integer''}}\nDescription: multiplier(first_number:
int, second_number: int) -> float - Useful for when you need to multiply two
numbers together.\n--\nFuntion Name: Delegate work to co-worker\nFuntion attributes:
{''coworker'': {''type'': ''string''}, ''task'': {''type'': ''string''}, ''context'':
{''type'': ''string''}}\nDescription: Delegate work to co-worker(coworker: str,
task: str, context: str) - Delegate a specific task to one of the following
co-workers: Researcher. The input to this tool should be the role of the coworker,
the task you want them to do, and ALL necessary context to exectue the task,
they know nothing about the task, so share absolute everything you know, don''t
reference things but instead explain them.\n--\nFuntion Name: Ask question to
co-worker\nFuntion attributes: {''coworker'': {''type'': ''string''}, ''question'':
{''type'': ''string''}, ''context'': {''type'': ''string''}}\nDescription: Ask
question to co-worker(coworker: str, question: str, context: str) - Ask a specific
question to one of the following co-workers: Researcher. The input to this tool
should be the role of the coworker, the question you have for them, and ALL
necessary context to ask the question properly, they know nothing about the
question, so share absolute everything you know, don''t reference things but
instead explain them.\n\nUse this text to inform a valid ouput schema:\nThought:
Do I need to use a tool? Yes\nAction: multiplier\nAction Input: {\"first_number\":
2, \"second_number\": 6}\n\nThe output should be formatted as a JSON instance
that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\":
{\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\":
\"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe
object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema.
The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere
is the output schema:\n```\n{\"properties\": {\"function_name\": {\"title\":
\"Function Name\", \"description\": \"The name of the function to be called.\",
\"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"description\":
\"A dictinary of arguments to be passed to the function.\", \"type\": \"object\"}},
\"required\": [\"function_name\", \"arguments\"]}\n```\n```"}], "model": "gpt-4",
"n": 1, "stream": false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2660'
content-type:
- application/json
cookie:
- _cfuvid=5kZVxJOsRfxObr9hLdehia3eWTY.wvyv.6QajmkP_hU-1707555174271-0-604800000;
__cf_bm=tE85KSJVLW2b9uFQ3HdC_0X9zKb3zvxn_XQrw65Lr5I-1707555174-1-ASbOkyjQPFYaEjdVU9A62Rq43RljO+iw67jesVCWW1SR/PnNWomyDmLymjV9qhbKx0TBnRfqMk7Mva8JQd1CH8A=
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.12.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.12.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SRTU/kMAyG7/0Vkc8d1GG+UI8rIXFBCCS0y1LUZlJPJ5A4IXE1rEb97yidL/aS
gx8/1mtnnwkBuoVSgNpKVtabyc1n+/Cof+3uP6Z/eupfdk/m9u7v/fPu5eG3hzwZbv2Oik/WlXLW
G2Tt6IBVQMmYpk5XxWqxWExX8xFY16JJWud5Mp8Uy+nsaGydVhihFK+ZEELsxzdloxa/oBRFfqpY
jFF2COW5SQgIzqQKyBh1ZEkM+QUqR4w0xm2apqJ9RUJUsOlJpcw1SYsVlKIC2xvW3mgMFeSHLhm6
3iJxTB2jObo6RK6pt+vUWorr/EQiKkftD7RMZKhoqKhpGjjGGs77GNf54NZpd+qNOdc3mnTc1gFl
dJSyR3b+oA+ZEG/j3fr/TgE+OOu5ZveBlAYui9lhHly+6EJnqyNkx9L8sOZFdkwI8V9ktPVGU4fB
Bz2eMeXMhuwbAAD//wMAyN+BGD0CAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 85331e5f68ac9e6b-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 08:52:56 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:
- '2318'
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:
- '299373'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 125ms
x-request-id:
- req_7dc4325f2fd56a09bfd04aa3b863488d
status:
code: 200
message: OK
- 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.TOOLS:\n------\nYou
have access to only the following tools:\n\nmultiplier: multiplier(first_number:
int, second_number: int) -> float - Useful for when you need to multiply two
numbers together.\nDelegate work to co-worker: Delegate work to co-worker(coworker:
str, task: str, context: str) - Delegate a specific task to one of the following
co-workers: Researcher. The input to this tool should be the role of the coworker,
the task you want them to do, and ALL necessary context to exectue the task,
they know nothing about the task, so share absolute everything you know, don''t
reference things but instead explain them.\nAsk question to co-worker: Ask question
to co-worker(coworker: str, question: str, context: str) - Ask a specific question
to one of the following co-workers: Researcher. The input to this tool should
be the role of the coworker, the question you have for them, and ALL necessary
context to ask the question properly, they know nothing about the question,
so share absolute everything you know, don''t reference things but instead explain
them.\n\nTo use a tool, please use the exact following format:\n\n```\nThought:
Do I need to use a tool? Yes\nAction: the tool you wanna use, should be one
of [multiplier, Delegate work to co-worker, Ask question to co-worker], just
the name.\nAction Input: Any and all relevant information input and context
for using the tool\nObservation: the result of using the tool\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: What is 2
tims 6? Return only the number.\nThought: Do I need to use a tool? Yes\nAction:
multiplier\nAction Input: {\"first_number\": 2, \"second_number\": 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:
- '2353'
content-type:
- application/json
cookie:
- _cfuvid=5kZVxJOsRfxObr9hLdehia3eWTY.wvyv.6QajmkP_hU-1707555174271-0-604800000;
__cf_bm=tE85KSJVLW2b9uFQ3HdC_0X9zKb3zvxn_XQrw65Lr5I-1707555174-1-ASbOkyjQPFYaEjdVU9A62Rq43RljO+iw67jesVCWW1SR/PnNWomyDmLymjV9qhbKx0TBnRfqMk7Mva8JQd1CH8A=
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.12.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.12.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SQS0/DMBCE7/kVK59blLRNW3JBlRASlwKCS3mocpNtanB2jb1RQaj/HTl9wcWH
mZ3Zb/2TAChTqQJUudFSNs72p5/V3eO2vW9rztJFPZo9P9DlYPE0b6fbserFBK/esZRj6qLkxlkU
w7S3S49aMLZmk3SS53k2GXdGwxXaGKud9Ef9dJwND4kNmxKDKuAlAQD46d7IRhV+qQLS3lFpMARd
oypOQwDKs42K0iGYIJpE9c5mySRIHe41wy0QYgXC0AYEDcJsr2DOr3RjSFuYUdiiLyAbqEPF7rTb
cu08ryIntdae9LUhEzZLjzowxT1B2O3juwTgrbux/YetnOfGyVL4AykW5tl036fO33l2s/xgCou2
f1LDYXIgVOE7CDbLtaEavfOmOzlyJrvkFwAA//8DANlC5ErpAQAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 85331e6f283b9e6b-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 08:52:57 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:
- '1076'
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:
- '299437'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 112ms
x-request-id:
- req_98d6376c782ee48c9f981dda9e4cd917
status:
code: 200
message: OK
- 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=5kZVxJOsRfxObr9hLdehia3eWTY.wvyv.6QajmkP_hU-1707555174271-0-604800000;
__cf_bm=tE85KSJVLW2b9uFQ3HdC_0X9zKb3zvxn_XQrw65Lr5I-1707555174-1-ASbOkyjQPFYaEjdVU9A62Rq43RljO+iw67jesVCWW1SR/PnNWomyDmLymjV9qhbKx0TBnRfqMk7Mva8JQd1CH8A=
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.12.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.12.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SQMW/CMBCF9/yKk2dASdokKBtdKrrQoVWHqkImOYiL7XPti1qE+O+VQ4B28fDe
fed375gACNWKGkTTSW6M09P5V7t6zVcPZBbpUvObLp9s2T+3++qx7MQkErT5xIYv1Kwh4zSyInu2
G4+SMW7NqrQqiiKr5oNhqEUdsZ3j6f00LbO7kehINRhEDe8JAMBxeGM22+KPqCGdXBSDIcgdivo6
BCA86agIGYIKLC2Lyc1syDLaIe5Lh9D1RlqQYR+AO4TFEpjA9JqV0wfIYXOAEqRtL65H7r09D0sb
vtFPIMtnYvzgdE2maec8beIVttf6qm+VVaFbe5SBbEwRmNwZPyUAH0MD/b+jhPNkHK+Z9mjjwqwo
zvvEreybm+ejycRS/6GqKhkTinAIjGa9VXaH3nk1FBJzJqfkFwAA//8DAHGERCIHAgAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 85331e76dc8f9e6b-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 08:52:59 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:
- '1406'
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:
- '299791'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 41ms
x-request-id:
- req_238138022aa1a41b8e8427631d50970e
status:
code: 200
message: OK
- 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 agentsTOOLS:\n------\nYou have access
to only the following tools:\n\nmultiplier: multiplier(first_number: int, second_number:
int) -> float - Useful for when you need to multiply two numbers together.\n\nTo
use a tool, please use the exact following format:\n\n```\nThought: Do I need
to use a tool? Yes\nAction: the tool you wanna use, should be one of [multiplier],
just the name.\nAction Input: Any and all relevant information input and context
for using the tool\nObservation: the result of using the tool\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: What is 2
times 6? Return only the number.\nThis is the context you''re 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:
- '1353'
content-type:
- application/json
cookie:
- _cfuvid=BMxGwK4wPoN6Cq5150swBY7QbtTvmWU2.p39x.cUidg-1703932144438-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.12.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.12.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SRzUvDQBDF7/krhjm30tjvXET0IipSUEGshHQzTVY3O+vuBJTS/102/fSyh/fm
Db83u0kAUJeYAaq6ENU40599l0+vA5o9Ttr5l6rvX8zi4frmdzGdT1Yp9mKCV5+k5JC6UNw4Q6LZ
7mzlqRCKW9PpYDoej9PpvDMaLsnEWOWkP+oPJulwn6hZKwqYwXsCALDp3shmS/rBDAa9g9JQCEVF
mB2HANCziQoWIegghRXsnUzFVsh2uM81t1UtGdwy3IElKkEY2kBQgDCbK3ijsLTXKpbJoGmNaGc0
+YMGd9a1ksFmiWvtg+S2bVbkl5jBZQ+WGEixLc/UyRb3JNtjBcOV87yKdW1rzFFfa6tDnXsqAtuI
G4TdLr5NAD66U7X/2qPz3DjJhb/IxoWXs3S3D0+/cnKHw70pLIU509NRsifE8BuEmnytbUXeed1d
LnIm2+QPAAD//wMA6ajhMTACAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 85331e815928fa4a-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 08:53:02 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=Ny4Y6DMnCaDhdMrk0.yEtZYAyfySLJ_cn.5y_yGQmQE-1707555182-1-Ad6o9N1fVvEN4kCGNS1Y4Fp1cER00DyQ7AQPGDRyMwCPpwzi1ON9eK6Yd7tLbnTOrg9EKKXdbdbCnHBem3yA7N0=;
path=/; expires=Sat, 10-Feb-24 09:23:02 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=EOhUXf9b9_QOfeleN81awDzrY5RByUbEJsA6dkxzMP8-1707555182145-0-604800000;
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:
- '2085'
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:
- '299685'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 62ms
x-request-id:
- req_0ebbf861fab020b2add4febc51c083a4
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "Return a valid schema for the
one tool you must use with its arguments and values.\n\nTools available:\n\nFuntion
Name: multiplier\nFuntion attributes: {''first_number'': {''type'': ''integer''},
''second_number'': {''type'': ''integer''}}\nDescription: multiplier(first_number:
int, second_number: int) -> float - Useful for when you need to multiply two
numbers together.\n\nUse this text to inform a valid ouput schema:\nThought:
Do I need to use a tool? Yes\nAction: multiplier\nAction Input: {\"first_number\":
2, \"second_number\": 6}\n\nThe output should be formatted as a JSON instance
that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\":
{\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\":
\"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe
object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema.
The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere
is the output schema:\n```\n{\"properties\": {\"function_name\": {\"title\":
\"Function Name\", \"description\": \"The name of the function to be called.\",
\"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"description\":
\"A dictinary of arguments to be passed to the function.\", \"type\": \"object\"}},
\"required\": [\"function_name\", \"arguments\"]}\n```\n```"}], "model": "gpt-4",
"n": 1, "stream": false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1494'
content-type:
- application/json
cookie:
- _cfuvid=EOhUXf9b9_QOfeleN81awDzrY5RByUbEJsA6dkxzMP8-1707555182145-0-604800000;
__cf_bm=Ny4Y6DMnCaDhdMrk0.yEtZYAyfySLJ_cn.5y_yGQmQE-1707555182-1-Ad6o9N1fVvEN4kCGNS1Y4Fp1cER00DyQ7AQPGDRyMwCPpwzi1ON9eK6Yd7tLbnTOrg9EKKXdbdbCnHBem3yA7N0=
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.12.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.12.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SRS4/UMBCE7/kVrT5n0Dx3RrmudsUFECs4AEEZj9NJDHY72B0GNMp/R868lksO
XfV1qsunDABNjQWg7pRo19vZ7lf94cvXx9X88++PL8+f1k/m3dNRnneP7/XxBfNE+MMP0nKl3mjv
ektiPJ9lHUgJpa2L7Xy72WwWu+UkOF+TTVjby2w9mz8sVhei80ZTxAK+ZQAAp+mbsnFNf7CAeX6d
OIpRtYTFzQSAwds0QRWjiaJYML+L2rMQT3HfUiAwERQcydpZ44NTIlSD4YRpAt+AdARRd+RUUfJ+
vy/5VDJAic3AOl1ZsXJUYgElusGK6a2hUGJ+dqnQDo5YYnJM5MSaEKXiwR2StYBlflUiac/1K+kh
KWPJ4/R3vBwy3hqwvu2DP6S2eLD2Nm8Mm9hVgVT0nK6N4vszPmYA36emh//Kwz5410sl/idxWrha
bs778P6od3W9u4jiRdlX1HaVXRJi/BuFXNUYbin0wUzFp5zZmP0DAAD//wMAJIQ9DG8CAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 85331e911c08fa4a-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 08:53:05 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:
- '2989'
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:
- '299662'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 67ms
x-request-id:
- req_cf4290379281a132751fbcb17c59da57
status:
code: 200
message: OK
- 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 agentsTOOLS:\n------\nYou have access
to only the following tools:\n\nmultiplier: multiplier(first_number: int, second_number:
int) -> float - Useful for when you need to multiply two numbers together.\n\nTo
use a tool, please use the exact following format:\n\n```\nThought: Do I need
to use a tool? Yes\nAction: the tool you wanna use, should be one of [multiplier],
just the name.\nAction Input: Any and all relevant information input and context
for using the tool\nObservation: the result of using the tool\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: What is 2
times 6? Return only the number.\nThis is the context you''re working with:\n12\nThought:
Do I need to use a tool? Yes\nAction: multiplier\nAction Input: {\"first_number\":
2, \"second_number\": 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:
- '1497'
content-type:
- application/json
cookie:
- _cfuvid=EOhUXf9b9_QOfeleN81awDzrY5RByUbEJsA6dkxzMP8-1707555182145-0-604800000;
__cf_bm=Ny4Y6DMnCaDhdMrk0.yEtZYAyfySLJ_cn.5y_yGQmQE-1707555182-1-Ad6o9N1fVvEN4kCGNS1Y4Fp1cER00DyQ7AQPGDRyMwCPpwzi1ON9eK6Yd7tLbnTOrg9EKKXdbdbCnHBem3yA7N0=
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.12.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.12.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SQS0/DMBCE7/kVK59b1DSEhlwQUkEgAVWFhCoeqlxnmxocr7G3ogX1vyOnL7j4
MLMz+61/EgChK1GCUAvJqnGmW3xWo9nV5PF7eDcZ18V8NL6Z3Kdr86TOn1eiExM0e0fF+9SJosYZ
ZE12ayuPkjG2poPeIM/ztMhbo6EKTYzVjrun3d5Zmu0SC9IKgyjhJQEA+GnfyGYrXIkSep290mAI
skZRHoYAhCcTFSFD0IGlZdE5mooso21xhwS3YBErYIJlQJDAROYCHujVXmsrDVza8IW+hLQvdhWb
w25DtfM0i5x2acxBn2urw2LqUQaycU9gctv4JgF4a29c/sMWzlPjeMr0gTYWZv1s2yeO33l003xn
MrE0f1JZkewIRVgHxmY617ZG77xuT46cySb5BQAA//8DAPd+nhHpAQAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 85331ea4eadffa4a-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 08:53:06 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:
- '994'
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:
- '299651'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 69ms
x-request-id:
- req_b2fa5c2a1c9913c75c92f7242d30478d
status:
code: 200
message: OK
- 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.\nThis is the context you''re 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:
- '942'
content-type:
- application/json
cookie:
- _cfuvid=EOhUXf9b9_QOfeleN81awDzrY5RByUbEJsA6dkxzMP8-1707555182145-0-604800000;
__cf_bm=Ny4Y6DMnCaDhdMrk0.yEtZYAyfySLJ_cn.5y_yGQmQE-1707555182-1-Ad6o9N1fVvEN4kCGNS1Y4Fp1cER00DyQ7AQPGDRyMwCPpwzi1ON9eK6Yd7tLbnTOrg9EKKXdbdbCnHBem3yA7N0=
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.12.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.12.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SQQU8CMRCF7/srJj0DYVdYCDcDSAwHE6MeNIaU7rBb6XZqOwQJ4b+bLgvopYf3
5k2/eccEQOhCTECoSrKqnemOv4snlc/2i8Ni4AbZ+9vrcj5dPj9sZ9M5iU5M0PoLFV9SPUW1M8ia
7NlWHiVj3JqO+qPhcJiO88aoqUATY6Xj7qDbz9O7NlGRVhjEBD4SAIBj80Y2W+CPmEC/c1FqDEGW
KCbXIQDhyURFyBB0YGlZdG6mIstoG9yXCqHa1dKCDNsAXCHcPwITKGnUzkhGyIB1jQHyDkhbXEYU
eY+KzQE8Bke2CLDXXEGa9UT70+mKaKh0ntbxHLsz5qpvtNWhWnmUgWzECUzuHD8lAJ9NFbt/1wnn
qXa8YtqijQvTfHjeJ26t39wsa00mluZPajxKWkIRDoGxXm20LdE7r5tmImdySn4BAAD//wMArPEP
rxACAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 85331eabff7ffa4a-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 08:53:08 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:
- '1163'
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:
- '299780'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 44ms
x-request-id:
- req_1e0c6ef6f09f0b90ac16b1d31fd58e4d
status:
code: 200
message: OK
- 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.TOOLS:\n------\nYou
have access to only the following tools:\n\nmultiplier: multiplier(first_number:
int, second_number: int) -> float - Useful for when you need to multiply two
numbers together.\nDelegate work to co-worker: Delegate work to co-worker(coworker:
str, task: str, context: str) - Delegate a specific task to one of the following
co-workers: Researcher. The input to this tool should be the role of the coworker,
the task you want them to do, and ALL necessary context to exectue the task,
they know nothing about the task, so share absolute everything you know, don''t
reference things but instead explain them.\nAsk question to co-worker: Ask question
to co-worker(coworker: str, question: str, context: str) - Ask a specific question
to one of the following co-workers: Researcher. The input to this tool should
be the role of the coworker, the question you have for them, and ALL necessary
context to ask the question properly, they know nothing about the question,
so share absolute everything you know, don''t reference things but instead explain
them.\nDelegate work to co-worker: Delegate work to co-worker(coworker: str,
task: str, context: str) - Delegate a specific task to one of the following
co-workers: Researcher. The input to this tool should be the role of the coworker,
the task you want them to do, and ALL necessary context to exectue the task,
they know nothing about the task, so share absolute everything you know, don''t
reference things but instead explain them.\nAsk question to co-worker: Ask question
to co-worker(coworker: str, question: str, context: str) - Ask a specific question
to one of the following co-workers: Researcher. The input to this tool should
be the role of the coworker, the question you have for them, and ALL necessary
context to ask the question properly, they know nothing about the question,
so share absolute everything you know, don''t reference things but instead explain
them.\n\nTo use a tool, please use the exact following format:\n\n```\nThought:
Do I need to use a tool? Yes\nAction: the tool you wanna use, 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:
Any and all relevant information input and context for using the tool\nObservation:
the result of using the tool\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:\nThe human asks the AI to multiply 2 by 6 and the
AI returns 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:
- '3213'
content-type:
- application/json
cookie:
- _cfuvid=5kZVxJOsRfxObr9hLdehia3eWTY.wvyv.6QajmkP_hU-1707555174271-0-604800000;
__cf_bm=tE85KSJVLW2b9uFQ3HdC_0X9zKb3zvxn_XQrw65Lr5I-1707555174-1-ASbOkyjQPFYaEjdVU9A62Rq43RljO+iw67jesVCWW1SR/PnNWomyDmLymjV9qhbKx0TBnRfqMk7Mva8JQd1CH8A=
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.12.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.12.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SRW0sDMRCF3/dXDPPcSmvthX2RoiKlQhUUKVbKNjvdjWYzMZkVtfS/S7Y3fcnD
OXOG70w2CQDqHFNAVWaiKmfao498Rnc3V9P5+DaoJ76ffj5MZj9+ys/WYCsmePVGSg6pM8WVMySa
7c5WnjKhuLU77Az7/X53NGqMinMyMVY4aV+0O4Nub58oWSsKmMJLAgCwad7IZnP6whQ6rYNSUQhZ
QZgehwDQs4kKZiHoIJkVbJ1MxVbINriPJddFKSlcM0zAEuUgDHUgyECYzSXMKSzsWMUyKVS1Ee2M
Jn/QYGJdLSlsFrjWPsjS1tWK/AJTOG/BAgMptvkfdbDFPcn2WMFw4TyvYl1bG3PU19rqUC49ZYFt
xA3CbhffJgCvzanqf+3Rea6cLIXfycaFw05vtw9Pv3JyewdTWDLzJ9UbJHtCDN9BqFqutS3IO6+b
y0XOZJv8AgAA//8DANObLFcwAgAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 85331eb5bb889e6e-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 08:53:10 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:
- '1865'
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:
- '299220'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 155ms
x-request-id:
- req_f9d083482588cfd68d861681f1d2a70a
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "Return a valid schema for the
one tool you must use with its arguments and values.\n\nTools available:\n\nFuntion
Name: multiplier\nFuntion attributes: {''first_number'': {''type'': ''integer''},
''second_number'': {''type'': ''integer''}}\nDescription: multiplier(first_number:
int, second_number: int) -> float - Useful for when you need to multiply two
numbers together.\n--\nFuntion Name: Delegate work to co-worker\nFuntion attributes:
{''coworker'': {''type'': ''string''}, ''task'': {''type'': ''string''}, ''context'':
{''type'': ''string''}}\nDescription: Delegate work to co-worker(coworker: str,
task: str, context: str) - Delegate a specific task to one of the following
co-workers: Researcher. The input to this tool should be the role of the coworker,
the task you want them to do, and ALL necessary context to exectue the task,
they know nothing about the task, so share absolute everything you know, don''t
reference things but instead explain them.\n--\nFuntion Name: Ask question to
co-worker\nFuntion attributes: {''coworker'': {''type'': ''string''}, ''question'':
{''type'': ''string''}, ''context'': {''type'': ''string''}}\nDescription: Ask
question to co-worker(coworker: str, question: str, context: str) - Ask a specific
question to one of the following co-workers: Researcher. The input to this tool
should be the role of the coworker, the question you have for them, and ALL
necessary context to ask the question properly, they know nothing about the
question, so share absolute everything you know, don''t reference things but
instead explain them.\n--\nFuntion Name: Delegate work to co-worker\nFuntion
attributes: {''coworker'': {''type'': ''string''}, ''task'': {''type'': ''string''},
''context'': {''type'': ''string''}}\nDescription: Delegate work to co-worker(coworker:
str, task: str, context: str) - Delegate a specific task to one of the following
co-workers: Researcher. The input to this tool should be the role of the coworker,
the task you want them to do, and ALL necessary context to exectue the task,
they know nothing about the task, so share absolute everything you know, don''t
reference things but instead explain them.\n--\nFuntion Name: Ask question to
co-worker\nFuntion attributes: {''coworker'': {''type'': ''string''}, ''question'':
{''type'': ''string''}, ''context'': {''type'': ''string''}}\nDescription: Ask
question to co-worker(coworker: str, question: str, context: str) - Ask a specific
question to one of the following co-workers: Researcher. The input to this tool
should be the role of the coworker, the question you have for them, and ALL
necessary context to ask the question properly, they know nothing about the
question, so share absolute everything you know, don''t reference things but
instead explain them.\n\nUse this text to inform a valid ouput schema:\nThought:
Do I need to use a tool? Yes\nAction: multiplier\nAction Input: {\"first_number\":
2, \"second_number\": 6}\n\nThe output should be formatted as a JSON instance
that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\":
{\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\":
\"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe
object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema.
The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere
is the output schema:\n```\n{\"properties\": {\"function_name\": {\"title\":
\"Function Name\", \"description\": \"The name of the function to be called.\",
\"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"description\":
\"A dictinary of arguments to be passed to the function.\", \"type\": \"object\"}},
\"required\": [\"function_name\", \"arguments\"]}\n```\n```"}], "model": "gpt-4",
"n": 1, "stream": false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3826'
content-type:
- application/json
cookie:
- _cfuvid=5kZVxJOsRfxObr9hLdehia3eWTY.wvyv.6QajmkP_hU-1707555174271-0-604800000;
__cf_bm=tE85KSJVLW2b9uFQ3HdC_0X9zKb3zvxn_XQrw65Lr5I-1707555174-1-ASbOkyjQPFYaEjdVU9A62Rq43RljO+iw67jesVCWW1SR/PnNWomyDmLymjV9qhbKx0TBnRfqMk7Mva8JQd1CH8A=
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.12.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.12.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SRQU/jMBCF7/kV1pzbVQOUprnCgQviBkKbVeI609Rgj409QUCV/76yW1q4+PDe
+0ZvxvtCCNA91ALUTrKy3syrt/5h+Py4rZ7unm/Maqy+Hr+emO9LXr8/wiwRbvOCir+pP8pZb5C1
o4OtAkrGNLVcLVbL5bJcL7JhXY8mYYPn+dV8cV1eHomd0woj1OJvIYQQ+/ymbtTjB9Qi81mxGKMc
EOpTSAgIziQFZIw6siSG2dlUjhgp1+26rqF9Q0I0sB1Jpc4tSYsN1KIBOxrW3mgMDcwOKRmG0SJx
TIlMZlaHyC2NdpOitbiYfTsRlaP+h3WdnKmhqaGu6+BYazrtY9zgg9uk3Wk05qRvNem4awPK6Ch1
j+z8AZ8KIf7lu42/TgE+OOu5ZfeKlAZWVXmYB+cvOruXq6PJjqU56+uyKo4NIX5GRttuNQ0YfND5
jKlnMRX/AQAA//8DADOMN0k9AgAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 85331ec22c139e6e-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 08:53:12 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:
- '2339'
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:
- '299083'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 183ms
x-request-id:
- req_3ce7d6aba5122535dc207e098f58a9e7
status:
code: 200
message: OK
- 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.TOOLS:\n------\nYou
have access to only the following tools:\n\nmultiplier: multiplier(first_number:
int, second_number: int) -> float - Useful for when you need to multiply two
numbers together.\nDelegate work to co-worker: Delegate work to co-worker(coworker:
str, task: str, context: str) - Delegate a specific task to one of the following
co-workers: Researcher. The input to this tool should be the role of the coworker,
the task you want them to do, and ALL necessary context to exectue the task,
they know nothing about the task, so share absolute everything you know, don''t
reference things but instead explain them.\nAsk question to co-worker: Ask question
to co-worker(coworker: str, question: str, context: str) - Ask a specific question
to one of the following co-workers: Researcher. The input to this tool should
be the role of the coworker, the question you have for them, and ALL necessary
context to ask the question properly, they know nothing about the question,
so share absolute everything you know, don''t reference things but instead explain
them.\nDelegate work to co-worker: Delegate work to co-worker(coworker: str,
task: str, context: str) - Delegate a specific task to one of the following
co-workers: Researcher. The input to this tool should be the role of the coworker,
the task you want them to do, and ALL necessary context to exectue the task,
they know nothing about the task, so share absolute everything you know, don''t
reference things but instead explain them.\nAsk question to co-worker: Ask question
to co-worker(coworker: str, question: str, context: str) - Ask a specific question
to one of the following co-workers: Researcher. The input to this tool should
be the role of the coworker, the question you have for them, and ALL necessary
context to ask the question properly, they know nothing about the question,
so share absolute everything you know, don''t reference things but instead explain
them.\n\nTo use a tool, please use the exact following format:\n\n```\nThought:
Do I need to use a tool? Yes\nAction: the tool you wanna use, 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:
Any and all relevant information input and context for using the tool\nObservation:
the result of using the tool\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:\nThe human asks the AI to multiply 2 by 6 and the
AI returns 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.\nThought:
Do I need to use a tool? Yes\nAction: multiplier\nAction Input: {\"first_number\":
2, \"second_number\": 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:
- '3357'
content-type:
- application/json
cookie:
- _cfuvid=5kZVxJOsRfxObr9hLdehia3eWTY.wvyv.6QajmkP_hU-1707555174271-0-604800000;
__cf_bm=tE85KSJVLW2b9uFQ3HdC_0X9zKb3zvxn_XQrw65Lr5I-1707555174-1-ASbOkyjQPFYaEjdVU9A62Rq43RljO+iw67jesVCWW1SR/PnNWomyDmLymjV9qhbKx0TBnRfqMk7Mva8JQd1CH8A=
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.12.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.12.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SQS0/DMBCE7/kVK59blJSmobmgIgSqhOgBCSEeqlxnm5o6XmNvHwj1vyOnL7j4
MLMz+61/EgChK1GCUAvJqnGme/VVTfTrzcOLXA6Lp/76eX4/3K5HZrJZ1mPRiQmafaLiY+pCUeMM
sia7t5VHyRhbsyIt8jzPhr3WaKhCE2O1426/mw6yy0NiQVphECW8JQAAP+0b2WyFW1FC2jkqDYYg
axTlaQhAeDJRETIEHVhaFp2zqcgy2hb3lmAMFrECJlgFBAlMZK7hkd7tnbbSwMiGDfoSsp44VOxO
uw3VztMsctqVMSd9rq0Oi6lHGcjGPYHJ7eO7BOCjvXH1D1s4T43jKdMSbSws+vm+T5y/8+xmR5OJ
pfmTGqTJgVCE78DYTOfa1uid1+3JkTPZJb8AAAD//wMAP0eFIukBAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 85331ed2f8159e6e-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 08:53:13 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:
- '1015'
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:
- '299186'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 162ms
x-request-id:
- req_cfa7c5a5ec642001c23ff034a7badf64
status:
code: 200
message: OK
- 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 multiply 2 by 6 and
the AI returns 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:
- '970'
content-type:
- application/json
cookie:
- _cfuvid=5kZVxJOsRfxObr9hLdehia3eWTY.wvyv.6QajmkP_hU-1707555174271-0-604800000;
__cf_bm=tE85KSJVLW2b9uFQ3HdC_0X9zKb3zvxn_XQrw65Lr5I-1707555174-1-ASbOkyjQPFYaEjdVU9A62Rq43RljO+iw67jesVCWW1SR/PnNWomyDmLymjV9qhbKx0TBnRfqMk7Mva8JQd1CH8A=
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.12.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.12.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SQS0/DMBCE7/kVK5/bKkmbFnJD4kARiAuCA0KV42xrU7+wNypV1f+OnPQBFx9m
9lvPziEDYKplNTAhOQnj9fjmu33ZVve+0VLiW1ksn/Obh6ft4/tyanI2SoRrvlDQmZoIZ7xGUs4O
tgjICdPWYpEvqqoqbme9YVyLOmEbT+PZOJ8X0xMhnRIYWQ0fGQDAoX9TNtviD6shH50VgzHyDbL6
MgTAgtNJYTxGFYlbYqOrKZwltH3cV4kgO8Mt8LiNQBLhbgnkwHSalNd7KKHZwxxopwQCty0gFxJI
GTxPB6Qu2AHmNu4wjKAoJ+z04fGSVLuND65JV9lO64u+VlZFuQrIo7MpVSTnB/yYAXz2jXT/jmQ+
OONpRW6LNvbFLoZ97Fr+1S2rk0mOuP6j52V2SsjiPhKa1VrZDQYfVF9Qypkds18AAAD//wMANLco
TBcCAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 85331edaae979e6e-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 08:53:15 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:
- '1613'
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:
- '299773'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 45ms
x-request-id:
- req_8a46ff46a03a9a60a088b949786292b9
status:
code: 200
message: OK
- 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 agentsTOOLS:\n------\nYou have access
to only the following tools:\n\nmultiplier: multiplier(first_number: int, second_number:
int) -> float - Useful for when you need to multiply two numbers together.\n\nTo
use a tool, please use the exact following format:\n\n```\nThought: Do I need
to use a tool? Yes\nAction: the tool you wanna use, should be one of [multiplier],
just the name.\nAction Input: Any and all relevant information input and context
for using the tool\nObservation: the result of using the tool\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:\nThe human asks
the AI to calculate 2 times 6, and the AI correctly responds with 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.\nThis is the context you''re 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:
- '1437'
content-type:
- application/json
cookie:
- _cfuvid=EOhUXf9b9_QOfeleN81awDzrY5RByUbEJsA6dkxzMP8-1707555182145-0-604800000;
__cf_bm=Ny4Y6DMnCaDhdMrk0.yEtZYAyfySLJ_cn.5y_yGQmQE-1707555182-1-Ad6o9N1fVvEN4kCGNS1Y4Fp1cER00DyQ7AQPGDRyMwCPpwzi1ON9eK6Yd7tLbnTOrg9EKKXdbdbCnHBem3yA7N0=
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.12.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.12.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SRzUsDMRDF7/tXDHNupR+26l5EKWK9iCKCWinb7HQ3mmRiMitK6f8u2X56yeG9
ecPvTVYZAOoSc0BVF6KsN93zr/LeDvlqeffoF9c3tw/P/en1q5/cD76rCXZSghcfpGSXOlFsvSHR
7Da2ClQIpa39s97ZaDTqX4xbw3JJJsUqL93Tbm/cH24TNWtFEXN4ywAAVu2b2FxJP5hDr7NTLMVY
VIT5fggAA5ukYBGjjlI4wc7BVOyEXIv7VHNT1ZLDhGEKjqgEYWgiQQHCbC7hheLMXalUJgfbGNHe
aAo7DabON5LDaoZLHaLMXWMXFGaYw6ADM4yk2JVH6niNW5L1voLhygdepLquMWavL7XTsZ4HKiK7
hBuF/Sa+zgDe21M1/9qjD2y9zIU/yaWFw95gsw8Pv3LkDremsBTmWB9lW0KMv1HIzpfaVRR80O3l
Eme2zv4AAAD//wMA/D8Y8DACAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 85331ee74b331692-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 08:53:17 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:
- '1472'
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:
- '299665'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 67ms
x-request-id:
- req_dca68a6f7c56d36fd10db138c8a07d7e
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "Return a valid schema for the
one tool you must use with its arguments and values.\n\nTools available:\n\nFuntion
Name: multiplier\nFuntion attributes: {''first_number'': {''type'': ''integer''},
''second_number'': {''type'': ''integer''}}\nDescription: multiplier(first_number:
int, second_number: int) -> float - Useful for when you need to multiply two
numbers together.\n\nUse this text to inform a valid ouput schema:\nThought:
Do I need to use a tool? Yes\nAction: multiplier\nAction Input: {\"first_number\":
2, \"second_number\": 6}\n\nThe output should be formatted as a JSON instance
that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\":
{\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\":
\"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe
object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema.
The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere
is the output schema:\n```\n{\"properties\": {\"function_name\": {\"title\":
\"Function Name\", \"description\": \"The name of the function to be called.\",
\"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"description\":
\"A dictinary of arguments to be passed to the function.\", \"type\": \"object\"}},
\"required\": [\"function_name\", \"arguments\"]}\n```\n```"}], "model": "gpt-4",
"n": 1, "stream": false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1494'
content-type:
- application/json
cookie:
- _cfuvid=EOhUXf9b9_QOfeleN81awDzrY5RByUbEJsA6dkxzMP8-1707555182145-0-604800000;
__cf_bm=Ny4Y6DMnCaDhdMrk0.yEtZYAyfySLJ_cn.5y_yGQmQE-1707555182-1-Ad6o9N1fVvEN4kCGNS1Y4Fp1cER00DyQ7AQPGDRyMwCPpwzi1ON9eK6Yd7tLbnTOrg9EKKXdbdbCnHBem3yA7N0=
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.12.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.12.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SRQW/bMAyF7/4VBM/OkLRx2vm4HbpbsWHYZRocRaZttRLlSfS6IvB/H+SkSXfx
4X189OPTsQBA22INaAYtxo9udf+7fQzVjz+fo/60jTK99I/fH145fHsev66xzI5weCIjb64PJvjR
kdjAJ2wiaaG8dXO3vquqavPxfgE+tOSyrR9ltV2td5vbs2MI1lDCGn4WAADH5ZuzcUt/sYZ1+aZ4
Skn3hPVlCABjcFlBnZJNolmwvEITWIiXuF8oEtgEMhC8kHOrLkSvRagFy9loCEK34GQG8rpWrHi/
3ys+KlbYTWzynQ1rTwprUOgnJ3Z0lqLCMs/o2E+eWFLmR4WdjUkanvwhj9RwU4LCRCZw+07dzYrn
5Vd4Tj5fTnahH2M45Hp4cu6id5ZtGppIOgXO5yUJ48k+FwC/lmqn/9rCMQY/SiPhmTgvvL2pTvvw
+opXut2coQTR7p1rtyvOCTG9JiHfdJZ7imO0S9M5ZzEX/wAAAP//AwAzEiOyYAIAAA==
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 85331ef2fcc11692-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 08:53:20 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:
- '2650'
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:
- '299661'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 67ms
x-request-id:
- req_6940f18dab107804798e162f3c660d1e
status:
code: 200
message: OK
- 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 agentsTOOLS:\n------\nYou have access
to only the following tools:\n\nmultiplier: multiplier(first_number: int, second_number:
int) -> float - Useful for when you need to multiply two numbers together.\n\nTo
use a tool, please use the exact following format:\n\n```\nThought: Do I need
to use a tool? Yes\nAction: the tool you wanna use, should be one of [multiplier],
just the name.\nAction Input: Any and all relevant information input and context
for using the tool\nObservation: the result of using the tool\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:\nThe human asks
the AI to calculate 2 times 6, and the AI correctly responds with 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.\nThis is the context you''re working with:\n12\nThought:
Do I need to use a tool? Yes\nAction: multiplier\nAction Input: {\"first_number\":
2, \"second_number\": 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:
- '1581'
content-type:
- application/json
cookie:
- _cfuvid=EOhUXf9b9_QOfeleN81awDzrY5RByUbEJsA6dkxzMP8-1707555182145-0-604800000;
__cf_bm=Ny4Y6DMnCaDhdMrk0.yEtZYAyfySLJ_cn.5y_yGQmQE-1707555182-1-Ad6o9N1fVvEN4kCGNS1Y4Fp1cER00DyQ7AQPGDRyMwCPpwzi1ON9eK6Yd7tLbnTOrg9EKKXdbdbCnHBem3yA7N0=
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.12.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.12.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SQQU8CMRCF7/srJj0vZhdY0L0YE0LCQQlHo4aU7rBUu53SDioS/rvpsoBeenhv
3ptvekgAhK5ECUJtJKvGmd7ttpp7X01Gn6Ge/jzS87ZZSJqZxb6eT0QaE7R6R8Xn1I2ixhlkTfZk
K4+SMbbm42xcFEU/y1ujoQpNjNWOe8NeNsoHXWJDWmEQJbwkAACH9o1stsJvUUKWnpUGQ5A1ivIy
BCA8magIGYIOLC2L9Goqsoy2xZ0QzMAiVsAEu4AggYnMPTzRq51qKw082PCFvoS8L7qK42W3odp5
WkVOuzPmoq+11WGz9CgD2bgnMLlT/JgAvLU37v5hC+epcbxk+kAbCwfD4alPXL/z6uZFZzKxNH9S
xV3SEYqwD4zNcq1tjd553Z4cOZNj8gsAAP//AwCzfxwV6QEAAA==
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 85331f05dd851692-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 08:53:23 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:
- '2516'
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:
- '299630'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 73ms
x-request-id:
- req_7581ccc086ee4ffc4f872ec93917fc5e
status:
code: 200
message: OK
- 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 correctly responds with 12.\n\nNew lines of conversation:\nHuman:
What is 2 times 6? Return only the number.\nThis is the context you''re 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:
- '1026'
content-type:
- application/json
cookie:
- _cfuvid=EOhUXf9b9_QOfeleN81awDzrY5RByUbEJsA6dkxzMP8-1707555182145-0-604800000;
__cf_bm=Ny4Y6DMnCaDhdMrk0.yEtZYAyfySLJ_cn.5y_yGQmQE-1707555182-1-Ad6o9N1fVvEN4kCGNS1Y4Fp1cER00DyQ7AQPGDRyMwCPpwzi1ON9eK6Yd7tLbnTOrg9EKKXdbdbCnHBem3yA7N0=
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.12.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.12.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SRzU7DMBCE73mKlc9plaS/yg0uqBKCA9wQqlxnm5g6XtfeUErVd0dOQwsXH2Y8
42/XpwRA6EqUIFQjWbXOjJb76pnd9GWF5vvp3u/lbu+W04fPrNt2jyKNCdp8oOLf1FhR6wyyJnux
lUfJGFvzRbaYzWZFNumNlio0MVY7Hk1H2TyfDImGtMIgSnhLAABO/RnZbIVfooQs/VVaDEHWKMrr
JQDhyURFyBB0YGlZpDdTkWW0Pe5rg9B0rbQgwy4ANwh3K2ACJY3qjGSEAli3GGAOfNAKU5C2gg1x
M+hDRpH3qNgcwWNwZKsAB80N5MVYDE+fr8yGaudpE+eznTFXfautDs3aowxkI19gcpf4OQF473fT
/RtXOE+t4zXTDm0szJeLS5+4fcPNLWaDycTS/NHzIhkIRTgGxna91bZG77zuVxU5k3PyAwAA//8D
AKiyW5YhAgAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 85331f165b551692-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 08:53:25 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:
- '1324'
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:
- '299759'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 48ms
x-request-id:
- req_ab2691963759194b30bfc25cb1dd5867
status:
code: 200
message: OK
version: 1
Reference in New Issue View Git Blame Copy Permalink