You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
langchain/libs/partners/ollama
Bagatur 8461934c2b
core[patch], integrations[patch]: convert TypedDict to tool schema support (#24641)
supports following UX

```python
    class SubTool(TypedDict):
        """Subtool docstring"""

        args: Annotated[Dict[str, Any], {}, "this does bar"]

    class Tool(TypedDict):
        """Docstring
        Args:
            arg1: foo
        """

        arg1: str
        arg2: Union[int, str]
        arg3: Optional[List[SubTool]]
        arg4: Annotated[Literal["bar", "baz"], ..., "this does foo"]
        arg5: Annotated[Optional[float], None]
```

- can parse google style docstring
- can use Annotated to specify default value (second arg)
- can use Annotated to specify arg description (third arg)
- can have nested complex types
2 months ago
..
langchain_ollama core[patch], integrations[patch]: convert TypedDict to tool schema support (#24641) 2 months ago
scripts ollama: init package (#23615) 2 months ago
tests make image inputs compatible with langchain_ollama (#24619) 2 months ago
.gitignore ollama: init package (#23615) 2 months ago
LICENSE ollama: init package (#23615) 2 months ago
Makefile ollama: release 0.1.0 (#24510) 2 months ago
README.md ollama: init package (#23615) 2 months ago
poetry.lock ollama: release 0.1.0 (#24510) 2 months ago
pyproject.toml all: add release notes to pypi (#24519) 2 months ago

README.md

langchain-ollama

This package contains the LangChain integration with Ollama

Installation

pip install -U langchain-ollama

You will also need to run the Ollama server locally. You can download it here.

Chat Models

ChatOllama class exposes chat models from Ollama.

from langchain_ollama import ChatOllama

llm = ChatOllama(model="llama3-groq-tool-use")
llm.invoke("Sing a ballad of LangChain.")

Embeddings

OllamaEmbeddings class exposes embeddings from Ollama.

from langchain_ollama import OllamaEmbeddings

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

LLMs

OllamaLLM class exposes LLMs from Ollama.

from langchain_ollama import OllamaLLM

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