langchain-oracledb
An integration package connecting Oracle Database and LangChain
Decision gist · record as of 2026-08-14
Yes, if you are building a LangChain RAG application on Oracle Database. The package is actively maintained, has low install friction, and no known vulnerabilities. The UPL-1.0 license is permissive but less standard—verify it aligns with your project before committing. The integration is well-documented with examples and covers the full RAG workflow.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires an active Oracle Database connection and valid credentials (username, password, DSN).
- Oracle Client libraries optional but some features require Thick mode.
- Low install friction with a pure-Python wheel.
License · maintenance · safety
UPL-1.0 (unclear) — Licensed under UPL-1.0 (Oracle Public License), which is permissive but less common than MIT or Apache 2.0. License treatment is marked unclear in metadata; verify compatibility with your project's license policy before adopting.
last release 2026-06-03 (72 days) · last repo commit 2026-08-14 · 59 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 149,307 downloads/mo, #10,997 on PyPI
Alternatives
Verify before relying
from langchain_oracledb.vectorstores import OracleVS
from langchain_oracledb.document_loaders.oracleai import OracleTextSplitter
import oracledb
conn = oracledb.connect(user=username, password=password, dsn=dsn)
vector_store = OracleVS(conn, embedding_model, "table_name", DistanceStrategy.EUCLIDEAN_DISTANCE)
vector_store.add_texts(["text"], [{"id": "1"}])
results = vector_store.similarity_search("query", 1)- Whether UPL-1.0 license is compatible with common commercial or open-source project licenses
- Performance characteristics and scalability limits for large vector stores
- Whether Thin mode (default) covers all use cases or if Thick mode with Oracle Client is often required in practice
What it is and what it does
langchain-oracledb bridges LangChain and Oracle Database, providing components to store and retrieve vector embeddings, load documents from Oracle tables, split text using Oracle's native capabilities, and generate embeddings. It is designed for building RAG pipelines that leverage Oracle's AI Vector Search feature.
The package exposes OracleVS for vector storage with similarity search, OracleDocLoader for loading documents from Oracle tables or files, OracleTextSplitter for chunking text by characters, words, or sentences, and OracleEmbeddings for generating embeddings. It depends on oracledb for database connectivity, langchain-core for the integration framework, and standard data-science libraries (numpy, pydantic). Connection to an Oracle Database is required; the package supports both Thin mode (no Oracle Client needed) and Thick mode (with Oracle Client libraries).
Use it for
- Build a RAG pipeline that stores document embeddings in Oracle and retrieves relevant chunks for LLM context
- Load large documents from Oracle tables, split them into chunks, and index them for semantic search
- Generate embeddings for text stored in Oracle Database and perform similarity searches within LangChain workflows
- Integrate Oracle Autonomous Database as a vector store backend for LangChain applications
- Process documents with Oracle's native text-splitting logic before ingesting into a vector store
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are building a LangChain RAG application on Oracle Database.
The package is actively maintained, has low install friction, and no known vulnerabilities. The UPL-1.0 license is permissive but less standard—verify it aligns with your project before committing. The integration is well-documented with examples and covers the full RAG workflow.
Install
langchain-oracledb on PyPI
Before you install
Low install friction with a pure-Python wheel. Actively maintained with recent releases; last commit 2026-08-14. Depends on langchain-core, langchain-text-splitters, numpy, oracledb, and pydantic—all standard ecosystem packages.
Requires an active Oracle Database connection and valid credentials (username, password, DSN). Oracle Client libraries optional but some features require Thick mode.
License in practice
Licensed under UPL-1.0 (Oracle Public License), which is permissive but less common than MIT or Apache 2.0. License treatment is marked unclear in metadata; verify compatibility with your project's license policy before adopting.
Quickstart
from langchain_oracledb.vectorstores import OracleVS
from langchain_oracledb.document_loaders.oracleai import OracleTextSplitter
import oracledb
conn = oracledb.connect(user=username, password=password, dsn=dsn)
vector_store = OracleVS(conn, embedding_model, "table_name", DistanceStrategy.EUCLIDEAN_DISTANCE)
vector_store.add_texts(["text"], [{"id": "1"}])
results = vector_store.similarity_search("query", 1)Verify before relying
- Whether UPL-1.0 license is compatible with common commercial or open-source project licenses
- Performance characteristics and scalability limits for large vector stores
- Whether Thin mode (default) covers all use cases or if Thick mode with Oracle Client is often required in practice
Package facts
| License | UPL-1.0 unclear |
| Python support | Supports the current Python release <4.0,>=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 5 packageslangchain-corelangchain-text-splittersnumpyoracledbpydantic |
| Maintenance | Actively maintained 72 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 149,307 / month, #10,997 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Programming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Programming Language :: Python :: 3.9 |
Evidence: langchain_oracledb-1.5.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “oracle database vector search”
- langchain-oracledbIntegrates Oracle Database with LangChain to enable vector search,…
- nano-vectordbA lightweight vector database that stores and queries embeddings with…
- pyobvectorpyobvector is a Python SDK for OceanBase Vector Store that provides…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also langchain-qdrant · langchain-oci · langchain-chroma · langchain-weaviate · langchain-unstructured · langchain-milvus · langchain-graph-retriever · langchain-elasticsearch · langchain-text-splitters · langchain-astradb