LangChain
=========

IBM integration with LangChain is available under `IBM and LangChain integration documentation <https://python.langchain.com/docs/integrations/providers/ibm>`_.

.. note::
    The ``langchain_ibm==0.3.x`` package relies on version ``0.3.x`` of the ``langchain_core`` package.

    For detailed migration instructions, please refer to the documentation `LangChain v0.3 <https://python.langchain.com/docs/versions/v0_3/>`_


Installation and Setup
----------------------

Install the integration package with

.. code-block::

    pip install -qU langchain-ibm

Get an IBM watsonx.ai api key and set it as an environment variable (``WATSONX_APIKEY``)

.. code-block:: python

    import os

    os.environ["WATSONX_APIKEY"] = "your IBM watsonx.ai api key"

Chat Model
----------

See a `usage example of Chat Model <https://python.langchain.com/docs/integrations/chat/ibm_watsonx/>`_

.. code-block:: python

    from langchain_ibm import ChatWatsonx

LLMs
----

See a `usage example of LLMs <https://python.langchain.com/docs/integrations/llms/ibm_watsonx/>`_

.. code-block:: python

    from langchain_ibm import WatsonxLLM

Embedding Models
----------------

See a `usage example of Embedding Models <https://python.langchain.com/docs/integrations/text_embedding/ibm_watsonx/>`_

.. code-block:: python

    from langchain_ibm import WatsonxEmbeddings

Rerank
------

See a `usage example of Rerank <https://python.langchain.com/docs/integrations/retrievers/ibm_watsonx_ranker/>`_

.. code-block:: python

    from langchain_ibm import WatsonxRerank

API reference
-------------

For detailed documentation of all IBM watsonx.ai features and configurations head to the API reference: `langchain-ibm <https://python.langchain.com/api_reference/ibm/index.html>`_