danielbalsam/surv_ai

A framework to empower forecasting using Large Language Models (LLMs)

surv_ai's Issues

hitting openAI rate limits

429, message='Too Many Requests', url=URL('https://api.openai.com/v1/chat/completions')
Traceback (most recent call last):
  File "[/mnt/Data/Projects/surv_ai/surv_ai/lib/llm/gpt.py](https://file+.vscode-resource.vscode-cdn.net/mnt/Data/Projects/surv_ai/surv_ai/lib/llm/gpt.py)", line 92, in _get_completion
    response.raise_for_status()
  File "[/Projects/surv_ai/venv/lib/python3.11/site-packages/aiohttp/client_reqrep.py](https://file+.vscode-resource.vscode-cdn.net/home/lawrence/Projects/surv_ai/venv/lib/python3.11/site-packages/aiohttp/client_reqrep.py)", line 1005, in raise_for_status
    raise ClientResponseError(
aiohttp.client_exceptions.ClientResponseError: 429, message='Too Many Requests', url=URL('https://api.openai.com/v1/chat/completions')
429, message='Too Many Requests', url=URL('https://api.openai.com/v1/chat/completions')
Traceback (most recent call last):
  File "[/mnt/Data/Projects/surv_ai/surv_ai/lib/llm/gpt.py](https://file+.vscode-resource.vscode-cdn.net/mnt/Data/Projects/surv_ai/surv_ai/lib/llm/gpt.py)", line 92, in _get_completion
    response.raise_for_status()
  File "[/Projects/surv_ai/venv/lib/python3.11/site-packages/aiohttp/client_reqrep.py](https://file+.vscode-resource.vscode-cdn.net/home/lawrence/Projects/surv_ai/venv/lib/python3.11/site-packages/aiohttp/client_reqrep.py)", line 1005, in raise_for_status
    raise ClientResponseError(
aiohttp.client_exceptions.ClientResponseError: 429, message='Too Many Requests', url=URL('https://api.openai.com/v1/chat/completions')

Wondering how you got around this, trying to run some of the examples...

examples don't work

from surv_ai import (
GPTClient,
Survey,
ToolBelt,
GoogleCustomSearchTool,
Knowledge
)

client = GPTClient(os.environ["OPEN_AI_API_KEY"])

survey = Survey(
client,
tool_belt=ToolBelt(
client,
tools=[
GoogleCustomSearchTool(
client,
os.environ["GOOGLE_API_KEY"],
os.environ["GOOGLE_SEARCH_ENGINE_ID"],
start_date="2023-01-01",
end_date="2023-05-01",
n_pages=10,
)
]
),
n_agents=10,
base_knowledge=[
Knowledge(
text="It is currently 2023/05/01, all the articles are from 2023.",
source="Additional context",
),
],
)

await survey.conduct(
"California experienced a significant amount of rainfall this winter.",
) # This should always returns high a confidence agreement.

---

TypeError Traceback (most recent call last)
Cell In[16], line 35
9 client = GPTClient(os.environ["OPEN_AI_API_KEY"])
11 survey = Survey(
12 client,
13 tool_belt=ToolBelt(
(...)
32 ],
33 )
---> 35 await survey.conduct(
36 "California experienced a significant amount of rainfall this winter.",
37 )

File C:\ProgramData\Anaconda3\lib\site-packages\surv_ai\core\survey.py:94, in Survey.conduct(self, hypothesis)
91 agents = 0
93 try:
---> 94 relevant_articles = await self.tool_belt.inspect(hypothesis, self.base_knowledge or [])
95 except NoMemoriesFoundException:
96 return SurveyResponse(
97 in_favor=0,
98 against=0,
(...)
102 uncertainty=0,
103 )

File C:\ProgramData\Anaconda3\lib\site-packages\surv_ai\lib\tools\tool_belt.py:84, in ToolBelt.inspect(self, original_prompt, base_knowledge, attempt)
81 knowledge += await tool.use(original_prompt, args)
83 if not knowledge and attempt < 3:
---> 84 knowledge = await self.inspect(original_prompt, attempt=attempt + 1)
85 elif not knowledge:
86 raise NoMemoriesFoundException()

TypeError: inspect() missing 1 required positional argument: 'base_knowledge'