`from llama_index.llms import Ollama

At a glance

The community member found some code online and is trying to run it, but is encountering issues with the imports. The community members provide suggestions to update the imports and install necessary dependencies. They also encounter issues with timeouts and maximum iterations, and provide solutions to increase the request timeout and max iterations. There is no explicitly marked answer, but the community members seem to have resolved the issues by the end of the comments.

Useful resources

LLucas

from llama_index.llms import Ollama
from llama_index.agent import ReActAgent
from llama_index.tools import FunctionTool
from datetime import date


def add_numbers(a : int, b: int) -> int:
    """Adds two numbers and returns the result"""
    return a+b

def get_current_date() -> date:
    """returns the current date"""
    return date.today()

tools = [
    FunctionTool.from_defaults(fn=add_numbers),
    FunctionTool.from_defaults(fn=get_current_date)
]

llm = Ollama(model="mistral")
agent = ReActAgent.from_tools(tools, llm=llm, verbose=True)
response = agent.chat("what is today's date?")

I found this code online and am trying to run it

I tried pip install llama_index but am getting

from llama_index.agent import ReActAgent
ImportError: cannot import name 'ReActAgent' from 'llama_index.agent' (unknown location)

Anyone know if the imports changed?

11 comments

LLogan M

Plain Text

from llama_index.llms.ollama import Ollama
from llama_index.core.agent import ReActAgent
from llama_index.core.tools import FunctionTool

You'll also need to install any integrations, i.e. pip install llama-index-llms-ollama

LLucas

from llama_index.llms import Ollama
ImportError: cannot import name 'Ollama' from 'llama_index.llms' (unknown location)

ok thank you! do you know how to fix this last one?

LLogan M

Need to install and update the import as above

LLucas

oops thanks I got it now,

Im scratching my head with this one

File "C:\Users\lhenry\AppData\Local\Programs\Python\Python312\Lib\site-packages\llama_index\llms\ollama\base.py", line 135, in chat
    response.raise_for_status()
  File "C:\Users\lhenry\AppData\Local\Programs\Python\Python312\Lib\site-packages\httpx\_models.py", line 761, in raise_for_status
    raise HTTPStatusError(message, request=request, response=self)
httpx.HTTPStatusError: Client error '404 Not Found' for url 'http://localhost:11434/api/chat'
For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
PS C:\Users\lhenry\Desktop\Projects\AIProject>

LLucas

nvm I got it, I had the run llm running

LLucas

File "C:\Users\lhenry\AppData\Local\Programs\Python\Python312\Lib\site-packages\httpx_transports\default.py", line 232, in handle_request
with map_httpcore_exceptions():
File "C:\Users\lhenry\AppData\Local\Programs\Python\Python312\Lib\contextlib.py", line 158, in exit
self.gen.throw(value)
File "C:\Users\lhenry\AppData\Local\Programs\Python\Python312\Lib\site-packages\httpx_transports\default.py", line 86, in map_httpcore_exceptions
raise mapped_exc(message) from exc
httpx.ReadTimeout: timed out

would running too slow cause this time out?

LLucas

it seems ot work with tinyllama

LLogan M

increase the request timeout

LLogan M

llm = Ollama(model="mistral", request_timeout=3600)

LLucas

File "C:\Users\lhenry\AppData\Local\Programs\Python\Python312\Lib\site-packages\llama_index\core\agent\react\step.py", line 412, in _get_response
raise ValueError("Reached max iterations.")
ValueError: Reached max iterations.

is there a similar way to up the max iterations?

LLucas

nvm got it

Add a reply

Find answers from the community

`from llama_index.llms import Ollama