mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-09 08:08:32 +00:00
af9e749edb
* Adding tool caching a loop execution prevention. This adds some guardrails, to both prevent the same tool to be used consecutively and also caching tool's results across the entire crew so it cuts down execution time and eventual LLM calls. This plays a huge role for smaller opensource models that usually fall into those behaviors patterns. It also includes some smaller improvements around the tool prompt and agent tools, all with the same intention of guiding models into better conform with agent instructions.
917 lines
33 KiB
YAML
917 lines
33 KiB
YAML
interactions:
|
|
- request:
|
|
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
|
|
personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following
|
|
tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
|
|
to multiply two numbers together.\n The input to this tool should be
|
|
a comma separated list of numbers of\n length two, representing the two
|
|
numbers you want to multiply together.\n For example, `1,2` would be
|
|
the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the
|
|
exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
|
|
the action to take, should be one of [multiplier], just the name.\nAction Input:
|
|
the input to the action\nObservation: the result of the action\n```\n\nWhen
|
|
you have a response for your task, or if you do not need to use a tool, you
|
|
MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
|
|
[your response here]\n```\n\t\tThis is the summary of your work so far:\n \nBegin!
|
|
This is VERY important to you, your job depends on it!\n\nCurrent Task: What
|
|
is 2 times 6?\n\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:
|
|
- '1219'
|
|
content-type:
|
|
- application/json
|
|
host:
|
|
- api.openai.com
|
|
user-agent:
|
|
- OpenAI/Python 1.6.1
|
|
x-stainless-arch:
|
|
- arm64
|
|
x-stainless-async:
|
|
- 'false'
|
|
x-stainless-lang:
|
|
- python
|
|
x-stainless-os:
|
|
- MacOS
|
|
x-stainless-package-version:
|
|
- 1.6.1
|
|
x-stainless-runtime:
|
|
- CPython
|
|
x-stainless-runtime-version:
|
|
- 3.11.7
|
|
method: POST
|
|
uri: https://api.openai.com/v1/chat/completions
|
|
response:
|
|
content: "{\n \"id\": \"chatcmpl-8b8NsTNQTMzHe8yjfHP8Eo31DhwBW\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1703861056,\n \"model\": \"gpt-4-0613\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
|
|
multiplier\\nAction Input: 2,6\"\n },\n \"logprobs\": null,\n \"finish_reason\":
|
|
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 261,\n \"completion_tokens\":
|
|
23,\n \"total_tokens\": 284\n },\n \"system_fingerprint\": null\n}\n"
|
|
headers:
|
|
CF-Cache-Status:
|
|
- DYNAMIC
|
|
CF-RAY:
|
|
- 83d2d1f00d1101c3-GRU
|
|
Cache-Control:
|
|
- no-cache, must-revalidate
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Fri, 29 Dec 2023 14:44:17 GMT
|
|
Server:
|
|
- cloudflare
|
|
Set-Cookie:
|
|
- __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=;
|
|
path=/; expires=Fri, 29-Dec-23 15:14:17 GMT; domain=.api.openai.com; HttpOnly;
|
|
Secure; SameSite=None
|
|
- _cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000;
|
|
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:
|
|
- '1750'
|
|
openai-version:
|
|
- '2020-10-01'
|
|
strict-transport-security:
|
|
- max-age=15724800; includeSubDomains
|
|
x-ratelimit-limit-requests:
|
|
- '10000'
|
|
x-ratelimit-limit-tokens:
|
|
- '300000'
|
|
x-ratelimit-limit-tokens_usage_based:
|
|
- '300000'
|
|
x-ratelimit-remaining-requests:
|
|
- '9999'
|
|
x-ratelimit-remaining-tokens:
|
|
- '299720'
|
|
x-ratelimit-remaining-tokens_usage_based:
|
|
- '299720'
|
|
x-ratelimit-reset-requests:
|
|
- 6ms
|
|
x-ratelimit-reset-tokens:
|
|
- 55ms
|
|
x-ratelimit-reset-tokens_usage_based:
|
|
- 55ms
|
|
x-request-id:
|
|
- 907b4e1c5dddb9abb47843bbab76cd7a
|
|
http_version: HTTP/1.1
|
|
status_code: 200
|
|
- request:
|
|
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
|
|
personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following
|
|
tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
|
|
to multiply two numbers together.\n The input to this tool should be
|
|
a comma separated list of numbers of\n length two, representing the two
|
|
numbers you want to multiply together.\n For example, `1,2` would be
|
|
the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the
|
|
exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
|
|
the action to take, should be one of [multiplier], just the name.\nAction Input:
|
|
the input to the action\nObservation: the result of the action\n```\n\nWhen
|
|
you have a response for your task, or if you do not need to use a tool, you
|
|
MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
|
|
[your response here]\n```\n\t\tThis is the summary of your work so far:\n \nBegin!
|
|
This is VERY important to you, your job depends on it!\n\nCurrent Task: What
|
|
is 2 times 6?\nThought: Do I need to use a tool? Yes\nAction: multiplier\nAction
|
|
Input: 2,6\nObservation: 12\nThought: \n"}], "model": "gpt-4", "n": 1, "stop":
|
|
["\nObservation"], "stream": false, "temperature": 0.7}'
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '1323'
|
|
content-type:
|
|
- application/json
|
|
cookie:
|
|
- __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=;
|
|
_cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000
|
|
host:
|
|
- api.openai.com
|
|
user-agent:
|
|
- OpenAI/Python 1.6.1
|
|
x-stainless-arch:
|
|
- arm64
|
|
x-stainless-async:
|
|
- 'false'
|
|
x-stainless-lang:
|
|
- python
|
|
x-stainless-os:
|
|
- MacOS
|
|
x-stainless-package-version:
|
|
- 1.6.1
|
|
x-stainless-runtime:
|
|
- CPython
|
|
x-stainless-runtime-version:
|
|
- 3.11.7
|
|
method: POST
|
|
uri: https://api.openai.com/v1/chat/completions
|
|
response:
|
|
content: "{\n \"id\": \"chatcmpl-8b8NuuCivtT2524QvfyDjrA3XkXLB\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1703861058,\n \"model\": \"gpt-4-0613\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"Do I need to use a tool? No\\nFinal Answer:
|
|
12\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
|
|
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 294,\n \"completion_tokens\":
|
|
15,\n \"total_tokens\": 309\n },\n \"system_fingerprint\": null\n}\n"
|
|
headers:
|
|
CF-Cache-Status:
|
|
- DYNAMIC
|
|
CF-RAY:
|
|
- 83d2d1fc79ad01c3-GRU
|
|
Cache-Control:
|
|
- no-cache, must-revalidate
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Fri, 29 Dec 2023 14:44:20 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:
|
|
- '2779'
|
|
openai-version:
|
|
- '2020-10-01'
|
|
strict-transport-security:
|
|
- max-age=15724800; includeSubDomains
|
|
x-ratelimit-limit-requests:
|
|
- '10000'
|
|
x-ratelimit-limit-tokens:
|
|
- '300000'
|
|
x-ratelimit-limit-tokens_usage_based:
|
|
- '300000'
|
|
x-ratelimit-remaining-requests:
|
|
- '9999'
|
|
x-ratelimit-remaining-tokens:
|
|
- '299695'
|
|
x-ratelimit-remaining-tokens_usage_based:
|
|
- '299695'
|
|
x-ratelimit-reset-requests:
|
|
- 6ms
|
|
x-ratelimit-reset-tokens:
|
|
- 60ms
|
|
x-ratelimit-reset-tokens_usage_based:
|
|
- 60ms
|
|
x-request-id:
|
|
- 5db441cfcc97cfd1ab228c2c0d5234f6
|
|
http_version: HTTP/1.1
|
|
status_code: 200
|
|
- request:
|
|
body: '{"messages": [{"role": "user", "content": "Progressively summarize the
|
|
lines of conversation provided, adding onto the previous summary returning a
|
|
new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
|
|
of artificial intelligence. The AI thinks artificial intelligence is a force
|
|
for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
|
|
intelligence is a force for good?\nAI: Because artificial intelligence will
|
|
help humans reach their full potential.\n\nNew summary:\nThe human asks what
|
|
the AI thinks of artificial intelligence. The AI thinks artificial intelligence
|
|
is a force for good because it will help humans reach their full potential.\nEND
|
|
OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: What
|
|
is 2 times 6?\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:
|
|
- '872'
|
|
content-type:
|
|
- application/json
|
|
cookie:
|
|
- __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=;
|
|
_cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000
|
|
host:
|
|
- api.openai.com
|
|
user-agent:
|
|
- OpenAI/Python 1.6.1
|
|
x-stainless-arch:
|
|
- arm64
|
|
x-stainless-async:
|
|
- 'false'
|
|
x-stainless-lang:
|
|
- python
|
|
x-stainless-os:
|
|
- MacOS
|
|
x-stainless-package-version:
|
|
- 1.6.1
|
|
x-stainless-runtime:
|
|
- CPython
|
|
x-stainless-runtime-version:
|
|
- 3.11.7
|
|
method: POST
|
|
uri: https://api.openai.com/v1/chat/completions
|
|
response:
|
|
content: "{\n \"id\": \"chatcmpl-8b8Nxf7bPMYpEdt2JmUIWLV4maYXG\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1703861061,\n \"model\": \"gpt-4-0613\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"The human asks the AI to calculate 2
|
|
times 6, and the AI responds with 12.\"\n },\n \"logprobs\": null,\n
|
|
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
|
149,\n \"completion_tokens\": 21,\n \"total_tokens\": 170\n },\n \"system_fingerprint\":
|
|
null\n}\n"
|
|
headers:
|
|
CF-Cache-Status:
|
|
- DYNAMIC
|
|
CF-RAY:
|
|
- 83d2d20fdf6f01c3-GRU
|
|
Cache-Control:
|
|
- no-cache, must-revalidate
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Fri, 29 Dec 2023 14:44:22 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:
|
|
- '1463'
|
|
openai-version:
|
|
- '2020-10-01'
|
|
strict-transport-security:
|
|
- max-age=15724800; includeSubDomains
|
|
x-ratelimit-limit-requests:
|
|
- '10000'
|
|
x-ratelimit-limit-tokens:
|
|
- '300000'
|
|
x-ratelimit-limit-tokens_usage_based:
|
|
- '300000'
|
|
x-ratelimit-remaining-requests:
|
|
- '9999'
|
|
x-ratelimit-remaining-tokens:
|
|
- '299796'
|
|
x-ratelimit-remaining-tokens_usage_based:
|
|
- '299796'
|
|
x-ratelimit-reset-requests:
|
|
- 6ms
|
|
x-ratelimit-reset-tokens:
|
|
- 40ms
|
|
x-ratelimit-reset-tokens_usage_based:
|
|
- 40ms
|
|
x-request-id:
|
|
- 99bc213367b851b629eb5489381887b7
|
|
http_version: HTTP/1.1
|
|
status_code: 200
|
|
- request:
|
|
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
|
|
personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following
|
|
tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
|
|
to multiply two numbers together.\n The input to this tool should be
|
|
a comma separated list of numbers of\n length two, representing the two
|
|
numbers you want to multiply together.\n For example, `1,2` would be
|
|
the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the
|
|
exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
|
|
the action to take, should be one of [multiplier], just the name.\nAction Input:
|
|
the input to the action\nObservation: the result of the action\n```\n\nWhen
|
|
you have a response for your task, or if you do not need to use a tool, you
|
|
MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
|
|
[your response here]\n```\n\t\tThis is the summary of your work so far:\n The
|
|
human asks the AI to calculate 2 times 6, and the AI responds with 12.\nBegin!
|
|
This is VERY important to you, your job depends on it!\n\nCurrent Task: What
|
|
is 3 times 3?\n\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream":
|
|
false, "temperature": 0.7}'
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '1293'
|
|
content-type:
|
|
- application/json
|
|
cookie:
|
|
- __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=;
|
|
_cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000
|
|
host:
|
|
- api.openai.com
|
|
user-agent:
|
|
- OpenAI/Python 1.6.1
|
|
x-stainless-arch:
|
|
- arm64
|
|
x-stainless-async:
|
|
- 'false'
|
|
x-stainless-lang:
|
|
- python
|
|
x-stainless-os:
|
|
- MacOS
|
|
x-stainless-package-version:
|
|
- 1.6.1
|
|
x-stainless-runtime:
|
|
- CPython
|
|
x-stainless-runtime-version:
|
|
- 3.11.7
|
|
method: POST
|
|
uri: https://api.openai.com/v1/chat/completions
|
|
response:
|
|
content: "{\n \"id\": \"chatcmpl-8b8NyS4i9PXuCQMD9p0Afb7msIFLA\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1703861062,\n \"model\": \"gpt-4-0613\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
|
|
multiplier\\nAction Input: 3,3\"\n },\n \"logprobs\": null,\n \"finish_reason\":
|
|
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 282,\n \"completion_tokens\":
|
|
23,\n \"total_tokens\": 305\n },\n \"system_fingerprint\": null\n}\n"
|
|
headers:
|
|
CF-Cache-Status:
|
|
- DYNAMIC
|
|
CF-RAY:
|
|
- 83d2d21a893d01c3-GRU
|
|
Cache-Control:
|
|
- no-cache, must-revalidate
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Fri, 29 Dec 2023 14:44:25 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:
|
|
- '2472'
|
|
openai-version:
|
|
- '2020-10-01'
|
|
strict-transport-security:
|
|
- max-age=15724800; includeSubDomains
|
|
x-ratelimit-limit-requests:
|
|
- '10000'
|
|
x-ratelimit-limit-tokens:
|
|
- '300000'
|
|
x-ratelimit-limit-tokens_usage_based:
|
|
- '300000'
|
|
x-ratelimit-remaining-requests:
|
|
- '9999'
|
|
x-ratelimit-remaining-tokens:
|
|
- '299703'
|
|
x-ratelimit-remaining-tokens_usage_based:
|
|
- '299703'
|
|
x-ratelimit-reset-requests:
|
|
- 6ms
|
|
x-ratelimit-reset-tokens:
|
|
- 59ms
|
|
x-ratelimit-reset-tokens_usage_based:
|
|
- 59ms
|
|
x-request-id:
|
|
- ac6d5063cae237481f45c88406ee1134
|
|
http_version: HTTP/1.1
|
|
status_code: 200
|
|
- request:
|
|
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
|
|
personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following
|
|
tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
|
|
to multiply two numbers together.\n The input to this tool should be
|
|
a comma separated list of numbers of\n length two, representing the two
|
|
numbers you want to multiply together.\n For example, `1,2` would be
|
|
the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the
|
|
exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
|
|
the action to take, should be one of [multiplier], just the name.\nAction Input:
|
|
the input to the action\nObservation: the result of the action\n```\n\nWhen
|
|
you have a response for your task, or if you do not need to use a tool, you
|
|
MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
|
|
[your response here]\n```\n\t\tThis is the summary of your work so far:\n The
|
|
human asks the AI to calculate 2 times 6, and the AI responds with 12.\nBegin!
|
|
This is VERY important to you, your job depends on it!\n\nCurrent Task: What
|
|
is 3 times 3?\nThought: Do I need to use a tool? Yes\nAction: multiplier\nAction
|
|
Input: 3,3\nObservation: 9\nThought: \n"}], "model": "gpt-4", "n": 1, "stop":
|
|
["\nObservation"], "stream": false, "temperature": 0.7}'
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '1396'
|
|
content-type:
|
|
- application/json
|
|
cookie:
|
|
- __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=;
|
|
_cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000
|
|
host:
|
|
- api.openai.com
|
|
user-agent:
|
|
- OpenAI/Python 1.6.1
|
|
x-stainless-arch:
|
|
- arm64
|
|
x-stainless-async:
|
|
- 'false'
|
|
x-stainless-lang:
|
|
- python
|
|
x-stainless-os:
|
|
- MacOS
|
|
x-stainless-package-version:
|
|
- 1.6.1
|
|
x-stainless-runtime:
|
|
- CPython
|
|
x-stainless-runtime-version:
|
|
- 3.11.7
|
|
method: POST
|
|
uri: https://api.openai.com/v1/chat/completions
|
|
response:
|
|
content: "{\n \"id\": \"chatcmpl-8b8O1OvQNcMLn5JwCShOrcdUGDYTQ\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1703861065,\n \"model\": \"gpt-4-0613\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"Do I need to use a tool? No\\nFinal Answer:
|
|
3 times 3 is 9.\"\n },\n \"logprobs\": null,\n \"finish_reason\":
|
|
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 315,\n \"completion_tokens\":
|
|
22,\n \"total_tokens\": 337\n },\n \"system_fingerprint\": null\n}\n"
|
|
headers:
|
|
CF-Cache-Status:
|
|
- DYNAMIC
|
|
CF-RAY:
|
|
- 83d2d22c1c5c01c3-GRU
|
|
Cache-Control:
|
|
- no-cache, must-revalidate
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Fri, 29 Dec 2023 14:44:27 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:
|
|
- '1885'
|
|
openai-version:
|
|
- '2020-10-01'
|
|
strict-transport-security:
|
|
- max-age=15724800; includeSubDomains
|
|
x-ratelimit-limit-requests:
|
|
- '10000'
|
|
x-ratelimit-limit-tokens:
|
|
- '300000'
|
|
x-ratelimit-limit-tokens_usage_based:
|
|
- '300000'
|
|
x-ratelimit-remaining-requests:
|
|
- '9999'
|
|
x-ratelimit-remaining-tokens:
|
|
- '299678'
|
|
x-ratelimit-remaining-tokens_usage_based:
|
|
- '299678'
|
|
x-ratelimit-reset-requests:
|
|
- 6ms
|
|
x-ratelimit-reset-tokens:
|
|
- 64ms
|
|
x-ratelimit-reset-tokens_usage_based:
|
|
- 64ms
|
|
x-request-id:
|
|
- 34020a2529f99325e63ed40493268cd1
|
|
http_version: HTTP/1.1
|
|
status_code: 200
|
|
- request:
|
|
body: '{"messages": [{"role": "user", "content": "Progressively summarize the
|
|
lines of conversation provided, adding onto the previous summary returning a
|
|
new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
|
|
of artificial intelligence. The AI thinks artificial intelligence is a force
|
|
for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
|
|
intelligence is a force for good?\nAI: Because artificial intelligence will
|
|
help humans reach their full potential.\n\nNew summary:\nThe human asks what
|
|
the AI thinks of artificial intelligence. The AI thinks artificial intelligence
|
|
is a force for good because it will help humans reach their full potential.\nEND
|
|
OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI to calculate 2 times 6,
|
|
and the AI responds with 12.\n\nNew lines of conversation:\nHuman: What is 3
|
|
times 3?\nAI: 3 times 3 is 9.\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:
|
|
- '959'
|
|
content-type:
|
|
- application/json
|
|
cookie:
|
|
- __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=;
|
|
_cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000
|
|
host:
|
|
- api.openai.com
|
|
user-agent:
|
|
- OpenAI/Python 1.6.1
|
|
x-stainless-arch:
|
|
- arm64
|
|
x-stainless-async:
|
|
- 'false'
|
|
x-stainless-lang:
|
|
- python
|
|
x-stainless-os:
|
|
- MacOS
|
|
x-stainless-package-version:
|
|
- 1.6.1
|
|
x-stainless-runtime:
|
|
- CPython
|
|
x-stainless-runtime-version:
|
|
- 3.11.7
|
|
method: POST
|
|
uri: https://api.openai.com/v1/chat/completions
|
|
response:
|
|
content: "{\n \"id\": \"chatcmpl-8b8O3IxMbwCemZSzKFeBXV2doGGt7\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1703861067,\n \"model\": \"gpt-4-0613\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"The human asks the AI to calculate 2
|
|
times 6 and 3 times 3, and the AI responds with 12 and 9 respectively.\"\n },\n
|
|
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
|
|
\ \"usage\": {\n \"prompt_tokens\": 176,\n \"completion_tokens\": 31,\n
|
|
\ \"total_tokens\": 207\n },\n \"system_fingerprint\": null\n}\n"
|
|
headers:
|
|
CF-Cache-Status:
|
|
- DYNAMIC
|
|
CF-RAY:
|
|
- 83d2d2395c4d01c3-GRU
|
|
Cache-Control:
|
|
- no-cache, must-revalidate
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Fri, 29 Dec 2023 14:44:30 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:
|
|
- '3030'
|
|
openai-version:
|
|
- '2020-10-01'
|
|
strict-transport-security:
|
|
- max-age=15724800; includeSubDomains
|
|
x-ratelimit-limit-requests:
|
|
- '10000'
|
|
x-ratelimit-limit-tokens:
|
|
- '300000'
|
|
x-ratelimit-limit-tokens_usage_based:
|
|
- '300000'
|
|
x-ratelimit-remaining-requests:
|
|
- '9999'
|
|
x-ratelimit-remaining-tokens:
|
|
- '299775'
|
|
x-ratelimit-remaining-tokens_usage_based:
|
|
- '299775'
|
|
x-ratelimit-reset-requests:
|
|
- 6ms
|
|
x-ratelimit-reset-tokens:
|
|
- 44ms
|
|
x-ratelimit-reset-tokens_usage_based:
|
|
- 44ms
|
|
x-request-id:
|
|
- 6a043e22366e13d63ad963dc01964533
|
|
http_version: HTTP/1.1
|
|
status_code: 200
|
|
- request:
|
|
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
|
|
personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following
|
|
tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
|
|
to multiply two numbers together.\n The input to this tool should be
|
|
a comma separated list of numbers of\n length two, representing the two
|
|
numbers you want to multiply together.\n For example, `1,2` would be
|
|
the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the
|
|
exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
|
|
the action to take, should be one of [multiplier], just the name.\nAction Input:
|
|
the input to the action\nObservation: the result of the action\n```\n\nWhen
|
|
you have a response for your task, or if you do not need to use a tool, you
|
|
MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
|
|
[your response here]\n```\n\t\tThis is the summary of your work so far:\n The
|
|
human asks the AI to calculate 2 times 6 and 3 times 3, and the AI responds
|
|
with 12 and 9 respectively.\nBegin! This is VERY important to you, your job
|
|
depends on it!\n\nCurrent Task: What is 2 times 6?\n\n"}], "model": "gpt-4",
|
|
"n": 1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
|
|
headers:
|
|
accept:
|
|
- application/json
|
|
accept-encoding:
|
|
- gzip, deflate
|
|
connection:
|
|
- keep-alive
|
|
content-length:
|
|
- '1326'
|
|
content-type:
|
|
- application/json
|
|
cookie:
|
|
- __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=;
|
|
_cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000
|
|
host:
|
|
- api.openai.com
|
|
user-agent:
|
|
- OpenAI/Python 1.6.1
|
|
x-stainless-arch:
|
|
- arm64
|
|
x-stainless-async:
|
|
- 'false'
|
|
x-stainless-lang:
|
|
- python
|
|
x-stainless-os:
|
|
- MacOS
|
|
x-stainless-package-version:
|
|
- 1.6.1
|
|
x-stainless-runtime:
|
|
- CPython
|
|
x-stainless-runtime-version:
|
|
- 3.11.7
|
|
method: POST
|
|
uri: https://api.openai.com/v1/chat/completions
|
|
response:
|
|
content: "{\n \"id\": \"chatcmpl-8b8O7429GQMpUZpPBK77gOoK8UnMY\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1703861071,\n \"model\": \"gpt-4-0613\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
|
|
multiplier\\nAction Input: 2,6\"\n },\n \"logprobs\": null,\n \"finish_reason\":
|
|
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 292,\n \"completion_tokens\":
|
|
23,\n \"total_tokens\": 315\n },\n \"system_fingerprint\": null\n}\n"
|
|
headers:
|
|
CF-Cache-Status:
|
|
- DYNAMIC
|
|
CF-RAY:
|
|
- 83d2d24e09bf01c3-GRU
|
|
Cache-Control:
|
|
- no-cache, must-revalidate
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Fri, 29 Dec 2023 14:44:32 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:
|
|
- '1369'
|
|
openai-version:
|
|
- '2020-10-01'
|
|
strict-transport-security:
|
|
- max-age=15724800; includeSubDomains
|
|
x-ratelimit-limit-requests:
|
|
- '10000'
|
|
x-ratelimit-limit-tokens:
|
|
- '300000'
|
|
x-ratelimit-limit-tokens_usage_based:
|
|
- '300000'
|
|
x-ratelimit-remaining-requests:
|
|
- '9999'
|
|
x-ratelimit-remaining-tokens:
|
|
- '299695'
|
|
x-ratelimit-remaining-tokens_usage_based:
|
|
- '299695'
|
|
x-ratelimit-reset-requests:
|
|
- 6ms
|
|
x-ratelimit-reset-tokens:
|
|
- 61ms
|
|
x-ratelimit-reset-tokens_usage_based:
|
|
- 61ms
|
|
x-request-id:
|
|
- 7807e472ac55a3cb9201c4eadfe13ee2
|
|
http_version: HTTP/1.1
|
|
status_code: 200
|
|
- request:
|
|
body: '{"messages": [{"role": "user", "content": "Progressively summarize the
|
|
lines of conversation provided, adding onto the previous summary returning a
|
|
new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
|
|
of artificial intelligence. The AI thinks artificial intelligence is a force
|
|
for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
|
|
intelligence is a force for good?\nAI: Because artificial intelligence will
|
|
help humans reach their full potential.\n\nNew summary:\nThe human asks what
|
|
the AI thinks of artificial intelligence. The AI thinks artificial intelligence
|
|
is a force for good because it will help humans reach their full potential.\nEND
|
|
OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI to calculate 2 times 6
|
|
and 3 times 3, and the AI responds with 12 and 9 respectively.\n\nNew lines
|
|
of conversation:\nHuman: What is 2 times 6?\nAI: 0\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:
|
|
- '978'
|
|
content-type:
|
|
- application/json
|
|
cookie:
|
|
- __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=;
|
|
_cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000
|
|
host:
|
|
- api.openai.com
|
|
user-agent:
|
|
- OpenAI/Python 1.6.1
|
|
x-stainless-arch:
|
|
- arm64
|
|
x-stainless-async:
|
|
- 'false'
|
|
x-stainless-lang:
|
|
- python
|
|
x-stainless-os:
|
|
- MacOS
|
|
x-stainless-package-version:
|
|
- 1.6.1
|
|
x-stainless-runtime:
|
|
- CPython
|
|
x-stainless-runtime-version:
|
|
- 3.11.7
|
|
method: POST
|
|
uri: https://api.openai.com/v1/chat/completions
|
|
response:
|
|
content: "{\n \"id\": \"chatcmpl-8b8O8FQhcRqwPnGUxFziRReKvggG1\",\n \"object\":
|
|
\"chat.completion\",\n \"created\": 1703861072,\n \"model\": \"gpt-4-0613\",\n
|
|
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
|
\"assistant\",\n \"content\": \"The human asks the AI to calculate 2
|
|
times 6 and 3 times 3, and the AI responds with 12 and 9 respectively. However,
|
|
when asked again to calculate 2 times 6, the AI incorrectly responds with 0.\"\n
|
|
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
|
|
\ ],\n \"usage\": {\n \"prompt_tokens\": 180,\n \"completion_tokens\":
|
|
52,\n \"total_tokens\": 232\n },\n \"system_fingerprint\": null\n}\n"
|
|
headers:
|
|
CF-Cache-Status:
|
|
- DYNAMIC
|
|
CF-RAY:
|
|
- 83d2d2582ae901c3-GRU
|
|
Cache-Control:
|
|
- no-cache, must-revalidate
|
|
Connection:
|
|
- keep-alive
|
|
Content-Encoding:
|
|
- gzip
|
|
Content-Type:
|
|
- application/json
|
|
Date:
|
|
- Fri, 29 Dec 2023 14:44:37 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:
|
|
- '4793'
|
|
openai-version:
|
|
- '2020-10-01'
|
|
strict-transport-security:
|
|
- max-age=15724800; includeSubDomains
|
|
x-ratelimit-limit-requests:
|
|
- '10000'
|
|
x-ratelimit-limit-tokens:
|
|
- '300000'
|
|
x-ratelimit-limit-tokens_usage_based:
|
|
- '300000'
|
|
x-ratelimit-remaining-requests:
|
|
- '9999'
|
|
x-ratelimit-remaining-tokens:
|
|
- '299770'
|
|
x-ratelimit-remaining-tokens_usage_based:
|
|
- '299770'
|
|
x-ratelimit-reset-requests:
|
|
- 6ms
|
|
x-ratelimit-reset-tokens:
|
|
- 45ms
|
|
x-ratelimit-reset-tokens_usage_based:
|
|
- 45ms
|
|
x-request-id:
|
|
- feb3958ca226769ce85f1b4a6ba649ac
|
|
http_version: HTTP/1.1
|
|
status_code: 200
|
|
version: 1
|