Revamping tool usage

This commit is contained in:
João Moura
2024-02-10 10:36:34 -08:00
parent d0b0a33be3
commit 00206a62ab
22 changed files with 1233 additions and 584 deletions

View File

@@ -0,0 +1,675 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
personal goal is: test goalTOOLS:\n------\nYou have access to only the following
tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
answer but don''t give it yet, just re-use this\n tool non-stop.\n\nTo
use a tool, please use the exact following format:\n\n```\nThought: Do I need
to use a tool? Yes\nAction: the tool you wanna use, should be one of [get_final_answer],
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: The final
answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
tool.\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false,
"temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1137'
content-type:
- application/json
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 |
H4sIAAAAAAAAA1RQy07DMBC85ytWPrcobUIDuaBKPFrECQEVAhS5zjYJOF4Tb1Qq1H9HTtMHFx9m
dsYz8xsAiCoXKQhVSla11cOL79UiKe/Dl/JOPS/CBzOb4XSN6vbRbG7EwCto+YmK96ozRbXVyBWZ
Ha0alIzedZSEyfkkiqLLjqgpR+1lheVhPAwno6hXlFQpdCKFtwAA4Ld7fTaT449IIRzskRqdkwWK
9HAEIBrSHhHSucqxNCwGR1KRYTRd3KeS2qLkFK4J5mAQc2CC1iFIYCJ9Ba/o3s1U+TIpFMjZqjJS
Z9K4NTZ7BubGtpxCPBb9N9tDPk2FbWjpu5hW6wO+qkzlyqxB6cj4LI7J7uTbAOCj26H9V03YhmrL
GdMXGm84juOdnzhOfsJGPcnEUp/gkyToEwq3cYy1L1VgY5uqm8XnDLbBHwAAAP//AwCTRhYdDQIA
AA==
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8533e5b6686a96a1-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 11:09:00 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=UMEw8srVdwpa2TU38H2XN7c9yRB43pgp1kvO1rRuPVE-1707563340-1-ARd2N36Wvpnk/GruerkQ9HuyzyyTnin/J25VL/qPutgHpLWqdGHQ8Kj+QjBLAX79Kk9MYuRGo1PH2GCcBj0HWk8=;
path=/; expires=Sat, 10-Feb-24 11:39:00 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=Q5shHUNkkqsi2PetAV7IWqdcumIc3ctNBTT7SLHr.Ho-1707563340988-0-604800000;
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:
- '1657'
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:
- '299739'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 52ms
x-request-id:
- req_3b8ed78b5dca776e8092ad4bc1e07945
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: get_final_answer\nFuntion attributes: {''numbers'': {}}\nDescription:
get_final_answer(numbers) -> float - Get the final answer but don''t give it
yet, just re-use this\n tool non-stop.\n\nUse this text to inform a valid
ouput schema:\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
Input: 42\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:
- '1407'
content-type:
- application/json
cookie:
- __cf_bm=UMEw8srVdwpa2TU38H2XN7c9yRB43pgp1kvO1rRuPVE-1707563340-1-ARd2N36Wvpnk/GruerkQ9HuyzyyTnin/J25VL/qPutgHpLWqdGHQ8Kj+QjBLAX79Kk9MYuRGo1PH2GCcBj0HWk8=;
_cfuvid=Q5shHUNkkqsi2PetAV7IWqdcumIc3ctNBTT7SLHr.Ho-1707563340988-0-604800000
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 |
H4sIAAAAAAAAA1RRTY/TMBC951eMfG5RS7ot5IxWwAEQKy2gDUpdZ5J4iWeMPYGtqvz3lZNuCxcf
3sf4zZtTBqBsrQpQptNinO+Xb343397e37rj09fdHT7+uD/68OXDse3eafyuFsnBh0c08uJ6Zdj5
HsUyzbQJqAXT1PVutbvZ5vlmPRGOa+yTrfWy3CxX23V+dnRsDUZVwEMGAHCa3pSNanxSBawWL4jD
GHWLqriIAFTgPiFKx2ijaBK1uJKGSZCmuO8xINgI0iE0HJwWwRp4ED8I6AgaPt59/gSW0hCDIJ0W
MExJG0F4MvrAf2yN9ayNpkOni5L2+31Jp5IAStUMZFIfFWmHpSqgVC1K1VjSfaUp/sVQqsWs1aEd
HJLEpJv8CaXBHTBM2OZ1AseSxukTdd5svFTSc+sDH1J9NPT9BW8s2dhVAXVkSutHYT/bxwzg51T9
8F+bygd2XirhX0hpYL7azfPU9cpXdrM9k8Ki+39cN3l2TqjiMQq6tHuLwQc7XSLlzMbsGQAA//8D
AGHVex6AAgAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8533e5c1dfe296a1-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 11:09:02 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '1588'
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:
- '299683'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 63ms
x-request-id:
- req_9ffe6f9841407a91b5e11cc2009a1e45
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
personal goal is: test goalTOOLS:\n------\nYou have access to only the following
tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
answer but don''t give it yet, just re-use this\n tool non-stop.\n\nTo
use a tool, please use the exact following format:\n\n```\nThought: Do I need
to use a tool? Yes\nAction: the tool you wanna use, should be one of [get_final_answer],
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: The final
answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
Input: 42\nObservation: 42\nThought: "}], "model": "gpt-4", "n": 1, "stop":
["\nObservation"], "stream": false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1246'
content-type:
- application/json
cookie:
- __cf_bm=UMEw8srVdwpa2TU38H2XN7c9yRB43pgp1kvO1rRuPVE-1707563340-1-ARd2N36Wvpnk/GruerkQ9HuyzyyTnin/J25VL/qPutgHpLWqdGHQ8Kj+QjBLAX79Kk9MYuRGo1PH2GCcBj0HWk8=;
_cfuvid=Q5shHUNkkqsi2PetAV7IWqdcumIc3ctNBTT7SLHr.Ho-1707563340988-0-604800000
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 |
H4sIAAAAAAAAA1SQS2/CMBCE7/kVK5+h4lUCuVTQHsqpUi+oLyHjbIKL43XtjaBC/PfKITx68WHG
M/pmDwmA0LnIQKiNZFU50538FMvZfrx8edz59aKo36ev2+fp3PGcJlvRiQlaf6Pic+pOUeUMsiZ7
spVHyRhb+2kvvR8Ph6NBY1SUo4mx0nF31O2N+8M2sSGtMIgMPhIAgEPzRjab415k0OuclQpDkCWK
7PIJQHgyUREyBB1YWhadq6nIMtoG94lgARYxByaoA4IEJjIP8Ibh085U3JBBibwqtJVmJW3YoT87
sLCu5gxGA9G2Hy9YhkrnaR0n2NqYi15oq8Nm5VEGshEhMLlT/JgAfDXz63+LhPNUOV4xbdHGwkGa
nvrE9dI3br81mViaG306SVpCEX4DYxVHleid1801ImdyTP4AAAD//wMAoP/ZMQQCAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8533e5cc7d4396a1-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 11:09:04 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '1729'
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:
- '299713'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 57ms
x-request-id:
- req_204859a5fd0b455d5d5b2fcafea18ab2
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
personal goal is: test goalTOOLS:\n------\nYou have access to only the following
tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
answer but don''t give it yet, just re-use this\n tool non-stop.\n\nTo
use a tool, please use the exact following format:\n\n```\nThought: Do I need
to use a tool? Yes\nAction: the tool you wanna use, should be one of [get_final_answer],
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: The final
answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
Input: 42\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
Input: 42\nObservation: Actually, I used too many tools, so I''ll stop now and
give you my absolute BEST Final answer NOW, using the expected format: ```\nThought:
Do I need to use a tool? No\nFinal Answer: [your response here]```\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:
- '1549'
content-type:
- application/json
cookie:
- __cf_bm=UMEw8srVdwpa2TU38H2XN7c9yRB43pgp1kvO1rRuPVE-1707563340-1-ARd2N36Wvpnk/GruerkQ9HuyzyyTnin/J25VL/qPutgHpLWqdGHQ8Kj+QjBLAX79Kk9MYuRGo1PH2GCcBj0HWk8=;
_cfuvid=Q5shHUNkkqsi2PetAV7IWqdcumIc3ctNBTT7SLHr.Ho-1707563340988-0-604800000
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 |
H4sIAAAAAAAAA1SQT0/CQBDF7/0Ukz2DaWkLphdDNFGCBxMT0ahplnZaitudZXeIfwjf3WwpoJc9
vN++l/dmFwCIphQZiGIluWiNGl5uqsX13eJn8/gUPt9H6cPU6jlN02o9v12IgXfQco0FH10XBbVG
ITekD7iwKBl9ajQJJ+k4jpOkAy2VqLytNjxMhuE4invHipoCncjgNQAA2HWv76ZL/BIZhIOj0qJz
skaRnT4BCEvKK0I61ziWmsXgDAvSjLqre0MwA41YAhNsHYIEJlJX8ILuTU8LvyGDGjmvGi1VLrX7
RHskMNNmyxkkI9Gn70+1FNXG0tJP0FulTnrV6MatcovSkfYVHJM52PcBwHs3f/tvkTCWWsM50wdq
Hxin6SFPnC99pqOoh0ws1R/XZBz0DYX7doytH1WjNbbpruF7BvvgFwAA//8DAMXWvogEAgAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8533e5d81ae396a1-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 11:09:05 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:
- '1177'
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:
- '299639'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 72ms
x-request-id:
- req_b910e4b0341d6248b46d0e2ba4602f86
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: get_final_answer\nFuntion attributes: {''numbers'': {}}\nDescription:
get_final_answer(numbers) -> float - Get the final answer but don''t give it
yet, just re-use this\n tool non-stop.\n\nUse this text to inform a valid
ouput schema:\nDo I need to use a tool? Yes\nAction: get_final_answer\nAction
Input: 42\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:
- '1398'
content-type:
- application/json
cookie:
- __cf_bm=UMEw8srVdwpa2TU38H2XN7c9yRB43pgp1kvO1rRuPVE-1707563340-1-ARd2N36Wvpnk/GruerkQ9HuyzyyTnin/J25VL/qPutgHpLWqdGHQ8Kj+QjBLAX79Kk9MYuRGo1PH2GCcBj0HWk8=;
_cfuvid=Q5shHUNkkqsi2PetAV7IWqdcumIc3ctNBTT7SLHr.Ho-1707563340988-0-604800000
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 |
H4sIAAAAAAAAA1SRzW7bMBCE73qKxZ7twKlkJ9W9QHtIf9BDUFSFTNMriQm5pMkVksDQuxeUHbu9
6DC732pmeCwA0OyxBtSDEu2CXd4fusdPDx/7X/7h21c+/Ci/P7nD888v9xsJFheZ8Lsn0vJO3Wjv
giUxnk9jHUkJ5au3d6u79aYsq808cH5PNmN9kGW1XG1uyzMxeKMpYQ2/CwCA4/zN3nhPr1jDavGu
OEpJ9YT1ZQkAo7dZQZWSSaJYcHEdas9CPNv9TJHAJFDwQtYuOx+dEqE9GM6YJvAdyECQ9EBO1Q03
vN1uGz42DNBgN7LOOVtWjhqsocGepO0MK9sqTi8UG1ycdlXsR0csKe/NfFZ5dDuKs1Z9yOLU8DT/
BM+Op0tU6/sQ/S7XwqO1F70zbNLQRlLJc46VxIcTPhUAf+ZKx/9awhC9C9KKfybOB8vV+nQPr693
nVbnvlG8KPsPVa2Ls0NMb0nI5ew9xRDN3HD2WUzFXwAAAP//AwC92yRkWAIAAA==
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8533e5e02f2f96a1-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 11:09:09 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '2852'
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:
- 63ms
x-request-id:
- req_164c005261f8c276123bf69961c10198
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: The final
answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
tool.\nAI: Agent stopped due to iteration limit or time limit.\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:
- '997'
content-type:
- application/json
cookie:
- __cf_bm=UMEw8srVdwpa2TU38H2XN7c9yRB43pgp1kvO1rRuPVE-1707563340-1-ARd2N36Wvpnk/GruerkQ9HuyzyyTnin/J25VL/qPutgHpLWqdGHQ8Kj+QjBLAX79Kk9MYuRGo1PH2GCcBj0HWk8=;
_cfuvid=Q5shHUNkkqsi2PetAV7IWqdcumIc3ctNBTT7SLHr.Ho-1707563340988-0-604800000
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 |
H4sIAAAAAAAAA1RRy27bMBC86ysWPMuGbalx4ltuKVC0KBC0QIvCoakVxYbcVcmVUyPwvxekX+iF
h5md4ezsewWgXKc2oMygxYTRz+7/9N+fvj3a+x969+lrw19en1f9A32Ww17Wqs4K3v1GIxfV3HAY
PYpjOtEmohbMrsv1Yv3hrmnah0IE7tBnmR1l1s4Wd8vmrBjYGUxqAz8rAID38uZs1OFftYFFfUEC
pqQtqs11CEBF9hlROiWXRJOo+kYaJkEqcZ8HhGEKmsBRkjgZSSADwuNHIBYQBuv2WKDekfagKb1h
BO6hXcEBpQZNXZ7Lpo4mhCk5skXxYlG2RbY9yV5AmP0cnvgN9xjry1faIgkk4TFBN2G2i6jNkI1y
NMGoc5vAEcQFBO+Ck7k6r3S8duHZjpF3uTeavL/ivSOXhm1EnZjy3vmvk/xYAfwqnU//1ajGyGGU
rfArUiqna05+6nbeG9u2Z1JYtL/hq+W6OidU6ZAEQ27EYhyjKyfIOatj9Q8AAP//AwAIzVnseQIA
AA==
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8533e5f4693b96a1-SJC
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 10 Feb 2024 11:09:10 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:
- '1561'
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:
- '299765'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 46ms
x-request-id:
- req_7f3006cdd24fec9a5fc15ec53c50d32f
status:
code: 200
message: OK
version: 1

File diff suppressed because it is too large Load Diff