mirror of
https://github.com/hwchase17/langchain.git
synced 2025-08-13 14:50:00 +00:00
572020c4d8
* Ensure access to local model during `ChatOllama` instantiation (#27720). This adds a new param `validate_model_on_init` (default: `true`) * Catch a few more errors from the Ollama client to assist users |
||
|---|---|---|
| .. | ||
| langchain_ollama | ||
| scripts | ||
| tests | ||
| .gitignore | ||
| LICENSE | ||
| Makefile | ||
| pyproject.toml | ||
| README.md | ||
| uv.lock | ||
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:
llama3.1deepseek-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.")
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")