llama-index-legacy
Interface between LLMs and your data
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires an LLM API key (OpenAI by default) and data directory to index; Python 3.8.1 or later.
- 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 · maintenance · safety
MIT (permissive) — MIT license permits commercial and private use with minimal restrictions, making it suitable for most production applications.
last release 2024-11-07 (645 days) · last repo commit 2026-08-14 · 51,641 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 2,347,955 downloads/mo, #3,116 on PyPI
Alternatives
Verify before relying
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")- 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
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 on it.
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
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.
Requires an LLM API key (OpenAI by default) and data directory to index; Python 3.8.1 or later.
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")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
| License | MIT permissive |
| Python support | Supports the current Python release <4.0,>=3.8.1 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 18 packagesSQLAlchemydataclasses-jsondeprecatedfsspechttpxnest-asyncionltknumpyopenaipandastenacitytiktokentyping-extensionstyping-inspectrequestsaiohttpnetworkxdirtyjson |
| Maintenance | Actively maintained 645 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 2,347,955 / month, #3,116 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: OSI Approved :: MIT LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.9Topic :: Scientific/Engineering :: Artificial IntelligenceTopic :: Software Development :: Libraries :: Application FrameworksTopic :: Software Development :: Libraries :: Python Modules |
Evidence: llama_index_legacy-0.9.48.post4-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 › “llm data framework”
- llama-index-legacyLlamaIndex Legacy is a data framework for building LLM applications…
- llama-indexLlamaIndex is a data framework that connects large language models to…
- ragasRagas provides objective metrics, test data generation, and…
Give your agent the search over MCP, or paste the wish link into any chat.
More Python Modules packages
Converts domain names between Unicode and ASCII-compatible encoding (Punycode) according to IDNA 2008 and Unicode Technical Standard 46, with security validation and broader script coverage than the standard library.
Install it if you work with internationalized domain names, need to validate domains, or use HTTP clients that depend on it transitively.
Setuptools is a Python build backend and package management tool that handles building, distributing, and installing Python packages, including support for C/C++ extension modules.
PyYAML parses and emits YAML 1.1 data format, enabling serialization and deserialization of configuration files and Python objects to and from human-readable YAML text.
Pydantic validates Python data structures against type hints, coercing and checking input at runtime to ensure it matches a declared schema.
Provides reusable metadata objects for use with PEP-593 `typing.Annotated` to express common constraints like bounds, collection sizes, and predicates on types.
Install it if you use or build libraries that need to express type constraints in a standardized, inspectable way—or if you want to annotate your own types with…
Provides runtime tools to inspect and introspect Python type annotations, enabling programmatic examination of type hints at execution time.
See also llama-index · llama-index-core · gptcache · llama-index-indices-managed-llama-cloud · llama-index-cli · llama-index-llms-openai-like · llama-index-vector-stores-redis · llama-index-vector-stores-qdrant · llama-index-readers-file · pypi