llama-index-legacy

What it is and what it does

LlamaIndex Legacy is a framework for augmenting language models with private data through structured indexing and retrieval. It sits between your data sources and LLM applications, handling ingestion, structuring into indices, and retrieval-augmented query execution. The package provides both high-level APIs for quick prototyping and lower-level customization points for advanced use cases.

The framework depends on core data science libraries (SQLAlchemy, pandas, numpy) for data handling, embedding and tokenization (tiktoken, openai), and async utilities (aiohttp, nest-asyncio). It supports multiple LLM backends and embedding providers. Data can be persisted to disk or kept in-memory, and query results are augmented with retrieved context before being sent to the LLM.

Use it for:

• Build a chatbot that answers questions about internal documentation or knowledge bases
• Create semantic search over large document collections without manual indexing
• Augment an LLM with domain-specific data for more accurate contextual responses
• Prototype a retrieval-augmented generation pipeline with minimal boilerplate
• Index and query structured data from SQL databases alongside unstructured documents

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

LlamaIndex Legacy is a data framework for building LLM applications that connects private data to language models through indexing, retrieval, and query interfaces.

Yes, if you are building an LLM application that needs to incorporate private data and are comfortable with the legacy version status. The package is actively maintained, has no known vulnerabilities, and offers a straightforward API for common retrieval tasks. However, verify whether migration to the current package is recommended for your use case, as this is explicitly a legacy release.

Install

llama-index-legacy on PyPI

pip install llama-index-legacy

uv add llama-index-legacy

poetry add llama-index-legacy

Installing llama-index-legacy

Before you install

Low friction install with 18 runtime dependencies including core data and ML libraries (SQLAlchemy, pandas, numpy, openai, tiktoken). Actively maintained with recent commits and no known vulnerabilities.

License in practice

MIT license permits commercial and private use with minimal restrictions, making it suitable for most production applications.

Quickstart

pip install llama-index-legacy

import os
os.environ["OPENAI_API_KEY"] = "YOUR_KEY"

from llama_index_legacy import VectorStoreIndex, SimpleDirectoryReader

documents = SimpleDirectoryReader("YOUR_DATA_DIRECTORY").load_data()
index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine()
query_engine.query("YOUR_QUESTION")

Requires an LLM API key (OpenAI by default) and data directory to index; Python 3.8.1 or later.

Verify before relying

• Whether this legacy version is still recommended or if migration to current package is advised
• Performance characteristics and scalability limits for large document collections
• Specific vector store backends supported beyond in-memory storage

Package facts

Evidence: llama_index_legacy-0.9.48.post4-py3-none-any.whl

Keywords: LLM, NLP, RAG, data, devtools, index, retrieval

Tags

More Python Modules packages

Further reading