langchain/libs/partners/ollama

langchain-ollama

This package contains the LangChain integration with Ollama

Installation

pip install -U langchain-ollama

For the package to work, you will need to install and run the Ollama server locally (download).

To run integration tests (make integration_tests), you will need the following models installed in your Ollama server:

• llama3.1
• deepseek-r1:1.5b

Install these models by running:

ollama pull <name-of-model>

Chat Models

ChatOllama class exposes chat models from Ollama.

from langchain_ollama import ChatOllama

llm = ChatOllama(model="llama3.1")
llm.invoke("Sing a ballad of LangChain.")

v1 Chat Models

For v1 chat models, you can use the ChatOllama class with the v1 namespace.

from langchain_ollama.v1.chat_models import ChatOllama

Embeddings

OllamaEmbeddings class exposes embeddings from Ollama.

from langchain_ollama import OllamaEmbeddings

embeddings = OllamaEmbeddings(model="llama3.1")
embeddings.embed_query("What is the meaning of life?")

LLMs

OllamaLLM class exposes traditional LLMs from Ollama.

from langchain_ollama import OllamaLLM

llm = OllamaLLM(model="llama3.1")
llm.invoke("The meaning of life is")