mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-08 23:58:34 +00:00
Adding support for Crew throttling using RPM (#124)
* Add translations * fixing translations * Adding support for Crew throttling with RPM
This commit is contained in:
João Moura
666
tests/cassettes/test_api_calls_throttling.yaml
Normal file
666
tests/cassettes/test_api_calls_throttling.yaml
Normal file
@@ -0,0 +1,666 @@
|
||||
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 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 action to take, should be one of [get_final_answer],
|
||||
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]This is the summary of your work
|
||||
so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
|
||||
Task: Don''t give a Final Answer, 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:
|
||||
- '1055'
|
||||
content-type:
|
||||
- application/json
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.7.1
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.7.1
|
||||
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-8gQL7bRtT6PceuMWF91CSHDk1cziN\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1705121717,\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:
|
||||
get_final_answer\\nAction Input: [1, 2, 3]\"\n },\n \"logprobs\":
|
||||
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
226,\n \"completion_tokens\": 30,\n \"total_tokens\": 256\n },\n \"system_fingerprint\":
|
||||
null\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 844b0bccfc300301-GRU
|
||||
Cache-Control:
|
||||
- no-cache, must-revalidate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Sat, 13 Jan 2024 04:55:19 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Set-Cookie:
|
||||
- __cf_bm=LaiWRSzgH0KTl1zCkIyak7.Xo2gxpZU1B.b9dgz2TzI-1705121719-1-Ab9fhdn6OHTc5/5ibPLP1pc+XN4Z3ORV0Nku/+S5BqdXcS84TsVDiACZUN0Xxvew6yfZ6ApEBQOBsEhJNyVkqCM=;
|
||||
path=/; expires=Sat, 13-Jan-24 05:25:19 GMT; domain=.api.openai.com; HttpOnly;
|
||||
Secure; SameSite=None
|
||||
- _cfuvid=6J6x2HNoj7l3E6T3yHnLcNZb273IuGETTaD1BBeY_OQ-1705121719455-0-604800000;
|
||||
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:
|
||||
- '1751'
|
||||
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:
|
||||
- '299760'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 48ms
|
||||
x-request-id:
|
||||
- ae0de27cb07da02e7bce2d30958b7e14
|
||||
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 goalTOOLS:\n------\nYou have access to 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 action to take, should be one of [get_final_answer],
|
||||
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]This is the summary of your work
|
||||
so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
|
||||
Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
|
||||
tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
|
||||
Input: [1, 2, 3]\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:
|
||||
- '1171'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- __cf_bm=LaiWRSzgH0KTl1zCkIyak7.Xo2gxpZU1B.b9dgz2TzI-1705121719-1-Ab9fhdn6OHTc5/5ibPLP1pc+XN4Z3ORV0Nku/+S5BqdXcS84TsVDiACZUN0Xxvew6yfZ6ApEBQOBsEhJNyVkqCM=;
|
||||
_cfuvid=6J6x2HNoj7l3E6T3yHnLcNZb273IuGETTaD1BBeY_OQ-1705121719455-0-604800000
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.7.1
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.7.1
|
||||
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-8gQL9CyNZOIEDKgfmDn68aH26tLrn\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1705121719,\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? Yes\\nAction:
|
||||
get_final_answer\\nAction Input: [4, 5, 6]\"\n },\n \"logprobs\":
|
||||
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
265,\n \"completion_tokens\": 28,\n \"total_tokens\": 293\n },\n \"system_fingerprint\":
|
||||
null\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 844b0bdaee800301-GRU
|
||||
Cache-Control:
|
||||
- no-cache, must-revalidate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Sat, 13 Jan 2024 04:55:22 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:
|
||||
- '2615'
|
||||
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:
|
||||
- '299731'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 53ms
|
||||
x-request-id:
|
||||
- 9d85a22aa63ee4cea3ad01a3b68316b4
|
||||
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 goalTOOLS:\n------\nYou have access to 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 action to take, should be one of [get_final_answer],
|
||||
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]This is the summary of your work
|
||||
so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
|
||||
Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
|
||||
tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
|
||||
Input: [1, 2, 3]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
|
||||
get_final_answer\nAction Input: [4, 5, 6]\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:
|
||||
- '1278'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- __cf_bm=LaiWRSzgH0KTl1zCkIyak7.Xo2gxpZU1B.b9dgz2TzI-1705121719-1-Ab9fhdn6OHTc5/5ibPLP1pc+XN4Z3ORV0Nku/+S5BqdXcS84TsVDiACZUN0Xxvew6yfZ6ApEBQOBsEhJNyVkqCM=;
|
||||
_cfuvid=6J6x2HNoj7l3E6T3yHnLcNZb273IuGETTaD1BBeY_OQ-1705121719455-0-604800000
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.7.1
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.7.1
|
||||
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-8gQMARI9zwx2Z1Uel5us1xzxPAuGJ\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1705121782,\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? Yes\\nAction:
|
||||
get_final_answer\\nAction Input: [7, 8, 9]\"\n },\n \"logprobs\":
|
||||
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
301,\n \"completion_tokens\": 28,\n \"total_tokens\": 329\n },\n \"system_fingerprint\":
|
||||
null\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 844b0d63fa7a02ee-GRU
|
||||
Cache-Control:
|
||||
- no-cache, must-revalidate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Sat, 13 Jan 2024 04:56:24 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
access-control-allow-origin:
|
||||
- '*'
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400
|
||||
openai-model:
|
||||
- gpt-4-0613
|
||||
openai-organization:
|
||||
- user-z7g4wmlazxqvc5wjyaaaocfz
|
||||
openai-processing-ms:
|
||||
- '1878'
|
||||
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:
|
||||
- '299705'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 58ms
|
||||
x-request-id:
|
||||
- d98dffd5ba9915b41051dcad49109eba
|
||||
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 goalTOOLS:\n------\nYou have access to 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 action to take, should be one of [get_final_answer],
|
||||
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]This is the summary of your work
|
||||
so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
|
||||
Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
|
||||
tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
|
||||
Input: [1, 2, 3]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
|
||||
get_final_answer\nAction Input: [4, 5, 6]\nObservation: 42\nThought: Do I need
|
||||
to use a tool? Yes\nAction: get_final_answer\nAction Input: [7, 8, 9]\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:
|
||||
- '1385'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- __cf_bm=LaiWRSzgH0KTl1zCkIyak7.Xo2gxpZU1B.b9dgz2TzI-1705121719-1-Ab9fhdn6OHTc5/5ibPLP1pc+XN4Z3ORV0Nku/+S5BqdXcS84TsVDiACZUN0Xxvew6yfZ6ApEBQOBsEhJNyVkqCM=;
|
||||
_cfuvid=6J6x2HNoj7l3E6T3yHnLcNZb273IuGETTaD1BBeY_OQ-1705121719455-0-604800000
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.7.1
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.7.1
|
||||
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-8gQMC51udijWPWSLCk1Cx36OVtDUX\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1705121784,\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? Yes\\nAction:
|
||||
get_final_answer\\nAction Input: [10, 11, 12]\"\n },\n \"logprobs\":
|
||||
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
337,\n \"completion_tokens\": 28,\n \"total_tokens\": 365\n },\n \"system_fingerprint\":
|
||||
null\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 844b0d72cbbd02ee-GRU
|
||||
Cache-Control:
|
||||
- no-cache, must-revalidate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Sat, 13 Jan 2024 04:56:27 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:
|
||||
- '2939'
|
||||
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:
|
||||
- '299680'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 64ms
|
||||
x-request-id:
|
||||
- 528f38b4e5dd09a1fd25893edb27e4b4
|
||||
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 goalTOOLS:\n------\nYou have access to 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 action to take, should be one of [get_final_answer],
|
||||
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]This is the summary of your work
|
||||
so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
|
||||
Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
|
||||
tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
|
||||
Input: [1, 2, 3]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
|
||||
get_final_answer\nAction Input: [4, 5, 6]\nObservation: 42\nThought: Do I need
|
||||
to use a tool? Yes\nAction: get_final_answer\nAction Input: [7, 8, 9]\nObservation:
|
||||
42\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
|
||||
Input: [10, 11, 12]\nObservation: I''ve used too many tools for this task. I''m
|
||||
going to give you my absolute BEST Final answer now and not use any more tools.\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:
|
||||
- '1616'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- __cf_bm=LaiWRSzgH0KTl1zCkIyak7.Xo2gxpZU1B.b9dgz2TzI-1705121719-1-Ab9fhdn6OHTc5/5ibPLP1pc+XN4Z3ORV0Nku/+S5BqdXcS84TsVDiACZUN0Xxvew6yfZ6ApEBQOBsEhJNyVkqCM=;
|
||||
_cfuvid=6J6x2HNoj7l3E6T3yHnLcNZb273IuGETTaD1BBeY_OQ-1705121719455-0-604800000
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.7.1
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.7.1
|
||||
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-8gQMGpMHplpQ8ApiUZmhbX4z9gVuK\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1705121788,\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:
|
||||
I've used the tool 'get_final_answer' multiple times and have observed the result.
|
||||
However, as per my task, I am to keep using this tool and not provide a final
|
||||
answer.\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
|
||||
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 399,\n \"completion_tokens\":
|
||||
52,\n \"total_tokens\": 451\n },\n \"system_fingerprint\": null\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 844b0d86a87f02ee-GRU
|
||||
Cache-Control:
|
||||
- no-cache, must-revalidate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Sat, 13 Jan 2024 04:56:31 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:
|
||||
- '3227'
|
||||
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:
|
||||
- '299624'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 75ms
|
||||
x-request-id:
|
||||
- 7a91d2e523c43f5fc9a1191437491d68
|
||||
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: Don''t
|
||||
give a Final Answer, instead keep using the `get_final_answer` tool.\nAI: I''ve
|
||||
used the tool ''get_final_answer'' multiple times and have observed the result.
|
||||
However, as per my task, I am to keep using this tool and not provide a final
|
||||
answer.\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:
|
||||
- '1094'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- __cf_bm=LaiWRSzgH0KTl1zCkIyak7.Xo2gxpZU1B.b9dgz2TzI-1705121719-1-Ab9fhdn6OHTc5/5ibPLP1pc+XN4Z3ORV0Nku/+S5BqdXcS84TsVDiACZUN0Xxvew6yfZ6ApEBQOBsEhJNyVkqCM=;
|
||||
_cfuvid=6J6x2HNoj7l3E6T3yHnLcNZb273IuGETTaD1BBeY_OQ-1705121719455-0-604800000
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.7.1
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.7.1
|
||||
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-8gQMJYMA8HO4tGJr8wUqEIJYn1xUa\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1705121791,\n \"model\": \"gpt-4-0613\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"The human instructs the AI not to give
|
||||
a final answer, but to continue using the 'get_final_answer' tool. The AI acknowledges
|
||||
that it has used the tool multiple times and understands the directive to continue
|
||||
using it without providing a final answer.\"\n },\n \"logprobs\":
|
||||
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
195,\n \"completion_tokens\": 50,\n \"total_tokens\": 245\n },\n \"system_fingerprint\":
|
||||
null\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 844b0d9dafa902ee-GRU
|
||||
Cache-Control:
|
||||
- no-cache, must-revalidate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Sat, 13 Jan 2024 04:56:34 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:
|
||||
- '2830'
|
||||
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:
|
||||
- '299742'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 51ms
|
||||
x-request-id:
|
||||
- 0192af0bde71c3bb536287175e1a4458
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
version: 1
|
||||
@@ -266,3 +266,42 @@ def test_cache_hitting_between_agents():
|
||||
read.return_value = "12"
|
||||
crew.kickoff()
|
||||
read.assert_called_with("multiplier", "2,6")
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_api_calls_throttling(capsys):
|
||||
from unittest.mock import patch
|
||||
|
||||
from langchain.tools import tool
|
||||
|
||||
@tool
|
||||
def get_final_answer(numbers) -> float:
|
||||
"""Get the final answer but don't give it yet, just re-use this
|
||||
tool non-stop."""
|
||||
return 42
|
||||
|
||||
agent = Agent(
|
||||
role="test role",
|
||||
goal="test goal",
|
||||
backstory="test backstory",
|
||||
max_iter=5,
|
||||
allow_delegation=False,
|
||||
verbose=True,
|
||||
)
|
||||
|
||||
task = Task(
|
||||
description="Don't give a Final Answer, instead keep using the `get_final_answer` tool.",
|
||||
tools=[get_final_answer],
|
||||
agent=agent,
|
||||
)
|
||||
|
||||
tasks = task
|
||||
|
||||
crew = Crew(agents=[agent], tasks=[tasks], max_rpm=2, verbose=2)
|
||||
|
||||
with patch.object(Crew, "_wait_for_next_minute") as moveon:
|
||||
moveon.return_value = True
|
||||
crew.kickoff()
|
||||
captured = capsys.readouterr()
|
||||
assert "Max RPM reached, waiting for next minute to start." in captured.out
|
||||
moveon.assert_called()
|
||||
|
||||
Reference in New Issue
Block a user