andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-10 08:38:30 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity
Files
91659d6488cebcd9114c33639639ddb8be293c06
crewAI/tests/cassettes/test_cache_hitting_between_agents.yaml
João Moura 00206a62ab Revamping tool usage
2024-02-10 10:36:34 -08:00

1925 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 |
H4sIAAAAAAAAA1SRT0/jMBDF7/kUozm3qN02Lc0FoYVDVyvgwIGWrqrUmSTedTzGniBQle+OnP5j
Lz68N2/0e+N9AoC6wAxQ1bmoxpnh9Vu5fljTapeuf3P4+evxfZk+vSzuqZwuHA5ignd/SckpdaW4
cYZEsz3YylMuFLeO56N5Opuk03FvNFyQibHKyXA6HM3Gk2OiZq0oYAavCQDAvn8jmy3oAzMYDU5K
QyHkFWF2HgJAzyYqmIegg+RWcHAxFVsh2+M+19xWtWRwx7AES1SAMLSBIAdhNjeworCxtyqWyaBp
jWhnNPmTBkvrWslgv8FS+yBb2zY78hvM4McANhhIsS2+qbMOjyTduYLhynnexbq2Neasl9rqUG89
5YFtxA3C7hDvEoA//ana/9qj89w42Qr/IxsXTuezwz68/MrFnUyOprDk5qKno0VyJMTwGYSabalt
Rd553V8uciZd8gUAAP//AwBVoBVzMAIAAA==
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8533eaa65ee36893-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 11:12:23 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=VUM_AzyPmw54UKYCZhrJdPu8KbJzn3N7bJOp_y.9Kyc-1707563543-1-AZT0SxUJP3NDQsM27IVGaO9UGlGGGZ1b3awpQUl9p3hTgm4X7fW6Gm29TusixoSADT4s/T+MAAy6Phf92Q+xsaw=;
path=/; expires=Sat, 10-Feb-24 11:42:23 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=ylta_5IzewtBbeSYSU3qahLvf8rnmBo7j6w87zjpbtc-1707563543431-0-604800000;
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:
- '1803'
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_c65d30cd6df3fbd0de8688f78e4a3aeb
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=ylta_5IzewtBbeSYSU3qahLvf8rnmBo7j6w87zjpbtc-1707563543431-0-604800000;
__cf_bm=VUM_AzyPmw54UKYCZhrJdPu8KbJzn3N7bJOp_y.9Kyc-1707563543-1-AZT0SxUJP3NDQsM27IVGaO9UGlGGGZ1b3awpQUl9p3hTgm4X7fW6Gm29TusixoSADT4s/T+MAAy6Phf92Q+xsaw=
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/kMAyG7/0Vkc+dVaEzHdTjLhIXFiHEXqCoTTOeTtjECYkrsRr1v6/S+YJL
Dn78WK+dfSYE6A3UAtROsrLeLG4+ti+Pv/QT3r3cL/uHP/3Nz4/1c3WrVr/vPiFPhuvfUfHJ+qGc
9QZZOzpgFVAypqlX62K9qsrVspyBdRs0SRs8L5aLoroqj8bOaYURavGaCSHEfn5TNtrgJ9SiyE8V
izHKAaE+NwkBwZlUARmjjiyJIb9A5YiR5rhd1zW0b0iIBrYjqZS5JWmxgVo0YEfD2huNoYH80CXD
MFokjqljNmdXh8gtjbZPrbW4zk8konK0+YKqRKaGpoa6roNjrOm8j3GDD65Pu9NozLm+1aTjrg0o
o6OUPbLzB33KhHib7zZ+OwX44Kznlt1fpDSwKsrDPLh80YWW6yNkx9J8sZZFdkwI8V9ktO1W04DB
Bz2fMeXMpuw/AAAA//8DAG2PnFw9AgAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8533eab518596893-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 11:12:26 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:
- '2207'
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_9a01ee74af99a1aedd8d368735f333f1
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=ylta_5IzewtBbeSYSU3qahLvf8rnmBo7j6w87zjpbtc-1707563543431-0-604800000;
__cf_bm=VUM_AzyPmw54UKYCZhrJdPu8KbJzn3N7bJOp_y.9Kyc-1707563543-1-AZT0SxUJP3NDQsM27IVGaO9UGlGGGZ1b3awpQUl9p3hTgm4X7fW6Gm29TusixoSADT4s/T+MAAy6Phf92Q+xsaw=
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 |
H4sIAAAAAAAAA1SQT2vCQBDF7/kUw561GGNiyKUUiuChQhtaSv8gazIm22524u6IFvG7l41R28se
3pv35jd7CACEKkUGoqglF02rh+lm/ZZvktljups/vYzTxfOm5vxhFu7z/FUMfIJWX1jwOXVTUNNq
ZEXmZBcWJaNvDaejaZxE8STpjIZK1D5WtTycDEdJGPWJmlSBTmTwHgAAHLrXs5kS9yKD0eCsNOic
rFBklyEAYUl7RUjnlGNpWAyuZkGG0XS49wRzMIglMMHWIUhgIn0LC/owM2WkhjvjdmgzCMeirzhe
dmuqWksrz2m2Wl/0tTLK1UuL0pHxexxTe4ofA4DP7sbtP2zRWmpaXjJ9o/GFcZie+sT1O69uGPcm
E0v9JxVFQU8o3I9jbJZrZSq0rVXdyZ4zOAa/AAAA//8DAHwOc//pAQAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8533eac3cc576893-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 11:12:27 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:
- '1440'
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_cbbe9abcc5b53c3c7928a5d15e08268d
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=ylta_5IzewtBbeSYSU3qahLvf8rnmBo7j6w87zjpbtc-1707563543431-0-604800000;
__cf_bm=VUM_AzyPmw54UKYCZhrJdPu8KbJzn3N7bJOp_y.9Kyc-1707563543-1-AZT0SxUJP3NDQsM27IVGaO9UGlGGGZ1b3awpQUl9p3hTgm4X7fW6Gm29TusixoSADT4s/T+MAAy6Phf92Q+xsaw=
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 |
H4sIAAAAAAAAA1SRy04DMQxF9/MVVtZT1JZOp3THohJIIBY8hIpQlWbcTmgSh8Qj+lD/HWX6gk0W
9/g61/YuAxC6EmMQqpasrDed0fdi+rJyT4/r1+Jt8s4P27Kc3I22X7J+noo8OWj+hYpPritF1htk
Te6AVUDJmLr2ym5ZDK+LQdkCSxWaZFt67gw63WHv+uioSSuMYgwfGQDArn1TNlfhWoyhm58UizHK
JYrxuQhABDJJETJGHVk6FvkFKnKMro37UiPUjZUOZFxF4Brh9h6YQEmjGiMZoQ+sLUYY5iBddSpR
FAIqNhsIGD25KsKP5rrFrrFzDNDrX4njp/tzWkNLH2ieJnONMWd9oZ2O9SygjORSssjkD/Z9BvDZ
bqX5N6jwgaznGdMKXWrYK4pDP3E5wIX2B0fIxNL8cZU32TGhiJvIaGcL7ZYYfNDtklLObJ/9AgAA
//8DAAExLRobAgAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8533eacd9ca26893-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 11:12:29 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:
- '1475'
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_d6b99d01f7fe1335ba2110b5bacf608a
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 |
H4sIAAAAAAAAA1SRS0/DMBCE7/kVqz23qG9KLqi8pN5AQkiUoip1tolbx2vsjQRU/e/I6ZOLDzM7
q2/W2wQAdY4poCozUZUz7fHXavb2cm+++WvmJnfFEz27zubxd7a244CtmODlmpQcU1eKK2dINNu9
rTxlQnFr97pzPRz1h4Obxqg4JxNjhZP2oN0ZdfuHRMlaUcAUPhIAgG3zRjab0zem0GkdlYpCyArC
9DQEgJ5NVDALQQfJrGDrbCq2QrbBfS25LkpJ4YFhCpYoB2GoA0EGwmxu4Z3C3E5ULJNCVRvRzmjy
Rw2m1tWSwnaOK+2DLGxdLcnPMYVeC+YYSLHNL9TRDg8ku1MFw4XzvIx1bW3MSV9pq0O58JQFthE3
CLt9fJcAfDanqv+1R+e5crIQ3pCNC3vj7n4fnn/l7Pb7B1NYMnOhdwfJgRDDTxCqFittC/LO6+Zy
kTPZJX8AAAD//wMAjGKIWjACAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8533ead98e9c6444-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 11:12:31 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=QNy.wYY1_9KHI8_RIeUZP.ali92DnVLjsO0oTX1XUfM-1707563551-1-AcwgNxZQVQEIE7HGXGP/Y7xskgkg3Jbu3L557XdSbkGcTUp12spKbI8e6GCb7fgn3Q+Zwuj+jMcX8oUH3M4djac=;
path=/; expires=Sat, 10-Feb-24 11:42:31 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=4YKuN.HwkkNnLgJwQBDQitCw85.UDIPaqBKt4otOGco-1707563551419-0-604800000;
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:
- '1658'
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_b2a5aa12c053cd45a20cd56c916a978f
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=4YKuN.HwkkNnLgJwQBDQitCw85.UDIPaqBKt4otOGco-1707563551419-0-604800000;
__cf_bm=QNy.wYY1_9KHI8_RIeUZP.ali92DnVLjsO0oTX1XUfM-1707563551-1-AcwgNxZQVQEIE7HGXGP/Y7xskgkg3Jbu3L557XdSbkGcTUp12spKbI8e6GCb7fgn3Q+Zwuj+jMcX8oUH3M4djac=
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 |
H4sIAAAAAAAAA1SRTW/bMAyG7/4VhM7OEDd1svnYy4oehh0GbOg8OIpM2+okSpPooUXg/z5I+eou
PvB5H5qkjgWA0L1oQKhJsrLerD7+GZ5/PD+F+vH1S5Dx7fO3vw/OvHytPj19fxBlMtzhBRVfrA/K
WW+QtaMTVgElY+pa7da7erup6yoD63o0SRs9r+5X6221ORuT0wqjaOBnAQBwzN80G/X4KhpYl5eK
xRjliKK5hgBEcCZVhIxRR5bEorxB5YiR8riPGBB0BJ4QBhesZMYeNCVHIbghk6gmtLJpab/ft3Rs
CaAVw0wqrdiRtNiKBlphZ8PaG42hFeUpJcM4WySOKZHN7OoQuaPZHlK0gbvyQiIqR/07tE1kaWnJ
fxfnLZbr+saNPrhDOhXNxlzrgyYdpy6gjI7SqpGdP+lLAfArn3n+73LCB2c9d+x+I6WGm7v61E/c
XvRG77dnyI6leWftquI8oYhvkdF2g6YRgw86Xz3NWSzFPwAAAP//AwBr2VHebAIAAA==
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8533eae4884a6444-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 11:12:34 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:
- '3367'
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_b56e83164780843a8b796fa55b469b1e
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=4YKuN.HwkkNnLgJwQBDQitCw85.UDIPaqBKt4otOGco-1707563551419-0-604800000;
__cf_bm=QNy.wYY1_9KHI8_RIeUZP.ali92DnVLjsO0oTX1XUfM-1707563551-1-AcwgNxZQVQEIE7HGXGP/Y7xskgkg3Jbu3L557XdSbkGcTUp12spKbI8e6GCb7fgn3Q+Zwuj+jMcX8oUH3M4djac=
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/srJj2DYVkWyF6MBjRoogeNJqghZXdYKt1ObYegEv476bKAXnp4
b96bb7qNAIQqRAYiX0rOK6vbw6/FdL7ajOOX60d9dzt+GpW/r9P753QibU+0QoLmn5jzMXWRU2U1
siJzsHOHkjG0xoPOIO0naZrWRkUF6hArLbd77U4/TprEklSOXmTwFgEAbOs3sJkCv0UGndZRqdB7
WaLITkMAwpEOipDeK8/SsGidzZwMo6lxRwQTMIgFMMHaI0hgIn0JD/RubpSRGq6M36DLIO6KpmJ3
2q2ptI7mgdOstT7pC2WUX84cSk8m7PFM9hDfRQAf9Y3rf9jCOqosz5hWaEJh0k0OfeL8nWc3ThuT
iaX+k0qGUUMo/I9nrGYLZUp01qn65MAZ7aI9AAAA//8DAEHO4tPpAQAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8533eafae9606444-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 11:12:36 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:
- '1087'
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_b09dc263c60d9ee4de53594d57b2b29e
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=4YKuN.HwkkNnLgJwQBDQitCw85.UDIPaqBKt4otOGco-1707563551419-0-604800000;
__cf_bm=QNy.wYY1_9KHI8_RIeUZP.ali92DnVLjsO0oTX1XUfM-1707563551-1-AcwgNxZQVQEIE7HGXGP/Y7xskgkg3Jbu3L557XdSbkGcTUp12spKbI8e6GCb7fgn3Q+Zwuj+jMcX8oUH3M4djac=
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/kVK59T1LQkQG8VXEBISMCpCFWus00Mjtd4NzxU9b8jpy+4+DCz
s/52NhmAsrWagTKtFtMFN7r8WC/MU3M5Kf28uF6Ee/m8Kh755q6fP1QqTwlavaGRQ+rMUBcciiW/
s01ELZi2Fhfji7KalmU1GB3V6FKsCTI6H42rYrpPtGQNsprBSwYAsBnexOZr/FYzGOcHpUNm3aCa
HYcAVCSXFKWZLYv2ovKTacgL+gH3uUVo+0570PzOIC3C/BaEwGhneqcFYQJiO2SoctC+PoxE5EC+
Zviy0g6ioRjRCGjPXxhzKCZnav/n9gjrqAmRVukw3zt31NfWW26XETWTT2AsFHbxbQbwOpTS/7tT
hUhdkKXQO/q0sKjK3T516v/kTg6mkGj3J3U1zvaEin9YsFuurW8whmiHjhJnts1+AQAA//8DAPLW
W1YaAgAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8533eb02782f6444-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 11:12:37 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:
- '1132'
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_61d34283c3b6d77c7ad9924085ad9e1d
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 calculate 2 times 6,
and the AI correctly responds with the number 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:
- '3233'
content-type:
- application/json
cookie:
- _cfuvid=ylta_5IzewtBbeSYSU3qahLvf8rnmBo7j6w87zjpbtc-1707563543431-0-604800000;
__cf_bm=VUM_AzyPmw54UKYCZhrJdPu8KbJzn3N7bJOp_y.9Kyc-1707563543-1-AZT0SxUJP3NDQsM27IVGaO9UGlGGGZ1b3awpQUl9p3hTgm4X7fW6Gm29TusixoSADT4s/T+MAAy6Phf92Q+xsaw=
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 |
H4sIAAAAAAAAA1SRzU7DMBCE73mK1Z5b1BLSVrkgJEDiwqlCAooq19kmBsdr7A0Cqr47cvrLxYcZ
z+gbe5MBoKmwBNSNEt16O5x9rl+q3/nX9/2suDPjx3c1/726eyLz1NgcBynBq3fSckhdaG69JTHs
drYOpIRS63g6mhaTvCimvdFyRTbFai/Dq+FoMt4X6oaNpoglvGYAAJv+TGyuom8sYTQ4KC3FqGrC
8ngJAAPbpKCK0URRTnBwMjU7Idfjzhvu6kZKuGV4AEdUgTB0kUCBMNtreKa4cDc6jSmh7awYbw2F
gwYPzndSwmaBaxOiLF3XrigssITLASwwkmZXnamTLe5JtscJlmsfeJXmus7ao742zsRmGUhFdgk3
CvtdfJsBvPVP1f1bjz5w62Up/EEuFU5Hxa4PT79ycvN8bwqLsmepfJbtCTH+RKF2uTaupuCD6V8u
cWbb7A8AAP//AwBUqF5vMAIAAA==
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8533eb0bcc2acfc4-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 11:12:39 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:
- '1402'
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:
- '299215'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 156ms
x-request-id:
- req_b2aded41145719a69d978de2b4845b64
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=ylta_5IzewtBbeSYSU3qahLvf8rnmBo7j6w87zjpbtc-1707563543431-0-604800000;
__cf_bm=VUM_AzyPmw54UKYCZhrJdPu8KbJzn3N7bJOp_y.9Kyc-1707563543-1-AZT0SxUJP3NDQsM27IVGaO9UGlGGGZ1b3awpQUl9p3hTgm4X7fW6Gm29TusixoSADT4s/T+MAAy6Phf92Q+xsaw=
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 |
H4sIAAAAAAAAA1SRzW7bMBCE73qKxZ7lwo5jx9Y9QIP23iJRIFDUSmZDLhlyBSQw9O4F5b/kwsN8
M4vZ5bEAQNNhBagPSrQLdrF775/7X3f977/248/2qV2+t4+uP/BPeR47LHPCt/9IyyX1Q3sXLInx
fMI6khLKU1cPy4fNdr3Z7GfgfEc2x4Ygi/vFcrtanxMHbzQlrOClAAA4zm/uxh19YAXL8qI4SkkN
hNXVBIDR26ygSskkUSxY3qD2LMRz3WPNADX2I+tct2HlqMYKanSjFROsoVhjeXKpOIyOWFJ2zMk5
a2KShkfXZmsFd+WFJNKeuy9om8lU84TnMtN1C+uHEH2bN+bR2qveGzbp0ERSyXNunMSHU3wqAF7n
a43fDoAhehekEf9GnAfudqvTPLx9zI2u789QvCh70/erTXFuiOkzCbmmNzxQDNHMx8s9i6n4DwAA
//8DADc96EEzAgAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8533eb15bb9fcfc4-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 11:12:42 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:
- '2698'
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_3083e7cc58f3bb3f7339a29d75e52a0c
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 calculate 2 times 6,
and the AI correctly responds with the number 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: I just used
the multiplier tool with input {''first_number'': 2, ''second_number'': 6}.
So I already know the result of that and don''t need to use it again now.\n\nThought:
"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3533'
content-type:
- application/json
cookie:
- _cfuvid=ylta_5IzewtBbeSYSU3qahLvf8rnmBo7j6w87zjpbtc-1707563543431-0-604800000;
__cf_bm=VUM_AzyPmw54UKYCZhrJdPu8KbJzn3N7bJOp_y.9Kyc-1707563543-1-AZT0SxUJP3NDQsM27IVGaO9UGlGGGZ1b3awpQUl9p3hTgm4X7fW6Gm29TusixoSADT4s/T+MAAy6Phf92Q+xsaw=
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 |
H4sIAAAAAAAAA1SQW0sDMRCF3/dXDHlupdt790UqWhGxIChSL5Q0O91NzWZiMsVL6X+XbG/6kodz
5pz5JpsEQOhcZCBUKVlVzjSHH8tn/Xg1ubson+4ffla3Tl1PZ92Zn/nxo2jEBC1WqPiQOlNUOYOs
ye5s5VEyxtZ00Br0+p1ev10bFeVoYqxw3Ow2W/20s0+UpBUGkcFLAgCwqd/IZnP8Ehm0GgelwhBk
gSI7DgEITyYqQoagA0vLonEyFVlGW+NeEtyARcyBCdYBQQITmXOY0qudaCsNjG34RJ9B2hb7iu1x
t6HCeVpETrs25qgvtdWhnHuUgWzcE5jcLr5NAN7qG9f/sIXzVDmeM72jjYWDYXfXJ07feXLT3t5k
Ymn+pEajZE8owndgrOZLbQv0zuv65MiZbJNfAAAA//8DAAKnQ8fpAQAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8533eb28c823cfc4-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 11:12:43 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:
- '1067'
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:
- '299143'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 171ms
x-request-id:
- req_ffb89b01f12636dbcb093c3d8ddadbbf
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 the number 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:
- '990'
content-type:
- application/json
cookie:
- _cfuvid=ylta_5IzewtBbeSYSU3qahLvf8rnmBo7j6w87zjpbtc-1707563543431-0-604800000;
__cf_bm=VUM_AzyPmw54UKYCZhrJdPu8KbJzn3N7bJOp_y.9Kyc-1707563543-1-AZT0SxUJP3NDQsM27IVGaO9UGlGGGZ1b3awpQUl9p3hTgm4X7fW6Gm29TusixoSADT4s/T+MAAy6Phf92Q+xsaw=
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 |
H4sIAAAAAAAAA1SRT08CMRDF7/spJj0D4Y8uyk0TY0g8GS9qDCndgS20ndqZjQLhu5suK+ilh/fm
TX7zeigAlK3UDJSptRgfXf/mc/W2uXo2Zv+yeZq/PjxPt5vt/T7Nm8enUvVygpYbNPKbGhjy0aFY
CifbJNSCeetoOpxel5PrctIanip0ObaO0r/qD8vRpEvUZA2ymsF7AQBwaN/MFir8VjMY9n4Vj8x6
jWp2HgJQiVxWlGa2LDqI6l1MQ0EwtLgvNULdeB1A85ZBaoS7OQiB0c40TgvCGMR6ZChBvqzBHuhQ
wZKk7vQuYyglNOJ2kJAjhYrhy+ahGiE0fokJRuOB6iiOZ3xH65homU8NjXNnfWWD5XqRUDOFjMpC
8RQ/FgAfbU3Nv8tVTOSjLIS2GLht+/a0T11+5OKOp50pJNr90Ydl0REq3rGgX6xsWGOKybatZc7i
WPwAAAD//wMAsxMr8CwCAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8533eb309c84cfc4-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 11:12:45 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:
- '1864'
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:
- '299767'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 46ms
x-request-id:
- req_ae872b8ad337e15d936b8bbb07e65510
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 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.\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:
- '1447'
content-type:
- application/json
cookie:
- _cfuvid=4YKuN.HwkkNnLgJwQBDQitCw85.UDIPaqBKt4otOGco-1707563551419-0-604800000;
__cf_bm=QNy.wYY1_9KHI8_RIeUZP.ali92DnVLjsO0oTX1XUfM-1707563551-1-AcwgNxZQVQEIE7HGXGP/Y7xskgkg3Jbu3L557XdSbkGcTUp12spKbI8e6GCb7fgn3Q+Zwuj+jMcX8oUH3M4djac=
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 |
H4sIAAAAAAAAA1SRT2vjMBDF7/4Uw5yTktbrNPhSCmWXsnsIpdAmzRIceWxrI2lUaQwtId+9yPnT
7EWH9+YNvzfaZQCoaywBVVeJst6MZ+/N0iy65uX33H78+lPMlvOfr4t8u2zIPuEoJXjzj5ScUleK
rTckmt3BVoEqobT1+nZyW0zzYloMhuWaTIq1XsY/xpPpdX5MdKwVRSzhLQMA2A1vYnM1fWAJk9FJ
sRRj1RKW5yEADGySglWMOkrlBEffpmIn5Abc5477tpMSHhgewRHVIAx9JKhAmM0dLCiu3L1KZUqw
vRHtjaZw0uDR+V5K2K2w0SHK2vV2Q2GFJdyMYIWRFLv6Qp3u8UiyP1cw3PrAm1TX9cac9UY7Hbt1
oCqyS7hR2B/i+wzg73Cq/r/26ANbL2vhLbm0MJ8Uh334/SsXbn40haUyl/osOxJi/IxCdt1o11Lw
QQ+XS5zZPvsCAAD//wMA/eb9lDACAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8533eb3d0a5ecfcc-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 11:12:47 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:
- '1516'
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_33c7525db9f28e60ae6827cc83f25cbe
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=4YKuN.HwkkNnLgJwQBDQitCw85.UDIPaqBKt4otOGco-1707563551419-0-604800000;
__cf_bm=QNy.wYY1_9KHI8_RIeUZP.ali92DnVLjsO0oTX1XUfM-1707563551-1-AcwgNxZQVQEIE7HGXGP/Y7xskgkg3Jbu3L557XdSbkGcTUp12spKbI8e6GCb7fgn3Q+Zwuj+jMcX8oUH3M4djac=
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 |
H4sIAAAAAAAAA1SRzW/UMBDF7/krRj5n0bb7RXOrAKlVxQkkJEiV9TqTxMWeCfYEWFb535GzX+3F
h3nvN3rzfMgAlK1VAcp0Wozv3ez9r+Y77R8/Pay4/oD+y+f7O/z47anb//s9/6ryRPDuBY2cqXeG
fe9QLNNRNgG1YNp6s5lvVuvFar2ZBM81uoS1vcyWs/n6ZnEiOrYGoyrgRwYAcJjelI1q/KsKmOfn
iccYdYuquJgAVGCXJkrHaKNoEpVfRcMkSFPcBwwINoKGP+jcrOHgtQjWYClhBoEbkA4hmg69Lkoq
abvdvkSmkg4lAZSqGcikWyvSHktVQKn84MT2zmIoVX506dAOHklickzkxNoQpaLB75K1gNv8rEQ0
TPUraZ2UsaRxSqBO54yXHhy3feBd6owG5y7zxpKNXRVQR6Z0cxTuj/iYATxPfQ9vKlR9YN9LJfwT
KS1c3K6O+9T1a6/q8u4kCot2r6jNMjslVHEfBX3VWGox9MFO9aec2Zj9BwAA//8DAFroJbR1AgAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8533eb47a9a2cfcc-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 11:12:49 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:
- '2133'
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_7c8fef4357ccf35a4bdd74ae47ee0b5e
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 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.\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: I just used
the multiplier tool with input {''first_number'': 2, ''second_number'': 6}.
So I already know the result of that and don''t need to use it again now.\n\nThought:
"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1747'
content-type:
- application/json
cookie:
- _cfuvid=4YKuN.HwkkNnLgJwQBDQitCw85.UDIPaqBKt4otOGco-1707563551419-0-604800000;
__cf_bm=QNy.wYY1_9KHI8_RIeUZP.ali92DnVLjsO0oTX1XUfM-1707563551-1-AcwgNxZQVQEIE7HGXGP/Y7xskgkg3Jbu3L557XdSbkGcTUp12spKbI8e6GCb7fgn3Q+Zwuj+jMcX8oUH3M4djac=
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 |
H4sIAAAAAAAAA1SQS2/CMBCE7/kVK5+hIg3PXKpWfUpVD6iX0lbIJEticLyuvRQo4r9XDgHaiw8z
O7PfehcBCJWLFERWSs4qq9vDr/nELjbdZPn28L12P2O6Gb+Oy+J5e7d8FK2QoNkCMz6mLjKqrEZW
ZA525lAyhtZ40Bn0+kmvP6qNinLUIVZYbnfbnX6cNImSVIZepPAeAQDs6jewmRw3IoVO66hU6L0s
UKSnIQDhSAdFSO+VZ2lYtM5mRobR1Li3BE9gEHNggpVHkMBE+gpe6MPcKyM1XBu/RpdCfCmaiv1p
t6bCOpoFTrPS+qTPlVG+nDqUnkzY45nsIb6PAD7rG1f/sIV1VFmeMi3RhMJk2D30ifN3nt2415hM
LPWf1GgUNYTCbz1jNZ0rU6CzTtUnB85oH/0CAAD//wMAfeDhj+kBAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8533eb55aaaccfcc-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 11:12:50 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:
- '896'
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:
- '299589'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 82ms
x-request-id:
- req_93d60fb3dc024e83dd1e316e838d5670
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 responds with the correct answer, 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:
- '1036'
content-type:
- application/json
cookie:
- _cfuvid=4YKuN.HwkkNnLgJwQBDQitCw85.UDIPaqBKt4otOGco-1707563551419-0-604800000;
__cf_bm=QNy.wYY1_9KHI8_RIeUZP.ali92DnVLjsO0oTX1XUfM-1707563551-1-AcwgNxZQVQEIE7HGXGP/Y7xskgkg3Jbu3L557XdSbkGcTUp12spKbI8e6GCb7fgn3Q+Zwuj+jMcX8oUH3M4djac=
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/kVI59b1LS02fYGQkLArrggpF2EKteZNgbb43gmKgj1v68cQgsX
H96bb/Tm+aMAULZWK1Cm0WJ8dONf7fZfe3N7/9b+vm6vqysKd5d/q8d5dzlr/6hRJmjzgka+qDND
PjoUS+HTNgm1YN5aVpNqvpjNq0lveKrRZWwXZXw+nizK2UA0ZA2yWsFTAQDw0b85W6jxTa2g53vF
I7PeoVodhwBUIpcVpZktiw6iRifTUBAMfdyHBqHpvA6g+ZVBGoSLGxACo53pnBaEKYj1yLAA2VuD
I9Chhg1JM+gDk5AjhZphb7PVIBhKCY1A6Dwma7QDHXiPaQTl9EwNcQ7HOxztYqJNvjl0zh31rQ2W
m3VCzRRyZhaKn/ihAHju++p+VKBiIh9lLfSKIS8sl0Nf6vQ1J3e6HEwh0e6bXi6LIaHidxb0660N
O0wx2b6+nLM4FP8BAAD//wMAlUo2rDUCAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8533eb5c1eeecfcc-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 11:12:52 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:
- '1693'
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:
- '299757'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 48ms
x-request-id:
- req_d1b20b6e01313a133c96666f353043c8
status:
code: 200
message: OK
version: 1
Reference in New Issue View Git Blame Copy Permalink