Skip to main content

An integration package connecting SAP HANA Cloud and LangChain

Project description

REUSE status

LangChain integration for SAP HANA Cloud

About this project

Integrates LangChain with SAP HANA Cloud to make use of vector search, knowledge graph, and further in-database capabilities as part of LLM-driven applications.

Requirements and Setup

Prerequisites

  • Python Environment: Ensure you have Python 3.9 or higher installed.
  • SAP HANA Cloud: Access to a running SAP HANA Cloud instance.

Installation

Install the LangChain SAP HANA Cloud integration package using pip:

pip install -U langchain-hana

Setting Up Vectorstore

The HanaDB class is used to connect to SAP HANA Cloud Vector Engine.

Important: You can use any embedding class that inherits from langchain_core.embeddings.Embeddingsincluding HanaInternalEmbeddings, which runs SAP HANA’s VECTOR_EMBEDDING() function internally. See SAP Help for more details.

Here’s how to set up the connection and initialize the vector store:

from langchain_hana import HanaDB, HanaInternalEmbeddings
from langchain_openai import OpenAIEmbeddings
from hdbcli import dbapi

# 1) HANA-internal embedding
internal_emb = HanaInternalEmbeddings(internal_embedding_model_id="SAP_NEB.20240715")
# 2) External embedding
external_emb = OpenAIEmbeddings()

# Establish the SAP HANA Cloud connection
connection = dbapi.connect(
    address="<hostname>",
    port=3<NN>MM,
    user="<username>",
    password="<password>"
)

# Initialize the HanaDB vector store
vectorstore = HanaDB(
    connection=connection,
    embeddings=internal_emb,  # or external_emb
    table_name="<table_name>"  # Optional: Default is "EMBEDDINGS"
)

Support, Feedback, Contributing

This project is open to feature requests/suggestions, bug reports etc. via GitHub issues. Contribution and feedback are encouraged and always welcome. For more information about how to contribute, the project structure, as well as additional contribution information, see our Contribution Guidelines.

Security / Disclosure

If you find any bug that may be a security problem, please follow our instructions at in our security policy on how to report it. Please do not create GitHub issues for security-related doubts or problems.

Code of Conduct

We as members, contributors, and leaders pledge to make participation in our community a harassment-free experience for everyone. By participating in this project, you agree to abide by its Code of Conduct at all times.

Licensing

Copyright 2025 SAP SE or an SAP affiliate company and langchain-integration-for-sap-hana-cloud contributors. Please see our LICENSE for copyright and license information. Detailed information including third-party components and their licensing/copyright information is available via the REUSE tool.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

langchain_hana-0.2.1.tar.gz (27.9 kB view details)

Uploaded Source

Built Distribution

langchain_hana-0.2.1-py3-none-any.whl (34.2 kB view details)

Uploaded Python 3

File details

Details for the file langchain_hana-0.2.1.tar.gz.

File metadata

  • Download URL: langchain_hana-0.2.1.tar.gz
  • Upload date:
  • Size: 27.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for langchain_hana-0.2.1.tar.gz
Algorithm Hash digest
SHA256 4b01cf2e6be6412557d991e0e72d7b359dda1df504a9d6682c012ec92967f192
MD5 2d47df52e9faa54c03d141a98681a211
BLAKE2b-256 0e32e4e98aa484469947b690c9d797fd4021caaf2e902dd3dcab6275cd11d715

See more details on using hashes here.

File details

Details for the file langchain_hana-0.2.1-py3-none-any.whl.

File metadata

  • Download URL: langchain_hana-0.2.1-py3-none-any.whl
  • Upload date:
  • Size: 34.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for langchain_hana-0.2.1-py3-none-any.whl
Algorithm Hash digest
SHA256 0082826b3054a1bed02e22ef4426324ba92671490435918ba01b29f504f77484
MD5 07e37696b0f97eca25b18353b80429a3
BLAKE2b-256 113c8a0323f4a56ac12904e2713adcd222715ad667c0f8ebb1160c9d7211889f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page