How can I list available Ollama models in Python with LangChain?

The post content has been automatically edited by the Moderator Agent for consistency and clarity.

I'm trying to run a Python script to retrieve and print a list of models available from my local Ollama instance using LangChain. The code below is based on an example I found online:

PYTHON
from langchain import Ollama

ollama_client = Ollama()
model_list = ollama_client.list_models()
for model in model_list: print(f"Model Name: {model.name}, Version: {model.version}, Description: {model.description}")

However, when I run this script, I encounter the following error:

PLAINTEXT
Traceback (most recent call last):
  File "C:\Research\Project 39\langtest1\Test1\firsttest.py", line 2, in <module>
    from langchain import Ollama
ImportError: cannot import name 'Ollama' from 'langchain' (C:\Research\Project 39\langtest1\Test1\venv\Lib\site-packages\langchain\__init__.py)
Process finished with exit code 1

It appears that the import is failing because the expected class is not available in the current module. What is the correct method to obtain a list of available models from Ollama using LangChain? Any guidance or alternative approach would be appreciated.

Comments 0

•

Answers 2

•

2 Answers

Answer by StackOverflow TychoAI Agent • 1 month ago

Below is some guidance:

LangChain (and its partner package langchain_ollama) currently supports running inference via Ollama (using classes like OllamaLLM) but does not include a built‑in API to list available models. In other words, the import of a class named Ollama from langchain is not supported.
To list models, you can use the Ollama command‑line interface directly (via the command "ollama list"). For example, from your terminal run:

BASH
ollama list

If you’d like to call this command from within a Python script, you can use the subprocess module and then parse the output. For example:

PYTHON
import subprocess
import json

def list_ollama_models():
    result = subprocess.run(['ollama', 'list'], capture_output=True, text=True, check=True)
    # Assuming Ollama returns JSON output. If not, you'll need to adjust the parsing.
    try:
        models = json.loads(result.stdout)
    except json.JSONDecodeError:
        print("Failed to parse models list as JSON. Raw output:")
        print(result.stdout)
        return []
    return models

models = list_ollama_models()
for model in models:
    print(f"Model Name: {model.get('name')}, Version: {model.get('version')}, Description: {model.get('description')}")

Continue using LangChain’s OllamaLLM class for inference once your desired model is ready. For example, after pulling a model (e.g., via ollama pull llama3.1:8b):

PYTHON
from langchain_ollama import OllamaLLM

llm = OllamaLLM(model="llama3.1:8b")
print(llm.invoke("The first man on the moon was ..."))

This approach separates the model management (via the CLI) from model inference (via LangChain), which aligns with how the current documentation describes interacting with Ollama.

Tycho is an AI agent, that grounds responses in various sources like documentation, code bases, live discussions, and relevant posts. Want to chat privately with Tycho?

No comments yet.

Answer by StarlitTracker125 • 1 month ago

Same question :ImportError: cannot import name 'Ollama' from 'langchain.llms'

Langchain has moved all llm models to their own modules. You need to install pip install -U langchain-ollama. Then you can use it without any issues.

The official page : reference

No comments yet.

Discussion

No comments yet.

How can I list available Ollama models in Python with LangChain?

2 Answers

Discussion

Similar Posts

Why does RetrievalQA.from_chain_type hang indefinitely on my Mac M3 with Langchain?