HippoRAG
HippoRAG is a RAG framework enabling LLMs to continuously integrate knowledge from external documents.
GraphCanon updated 3w · GitHub synced 3w · 26 views this month
Decision brief
HippoRAG is a RAG framework that leverages Knowledge Graphs and Personalized PageRank for improved information retrieval from external documents.
Good fit when
- When integrating human-like long-term memory capabilities into LLM models to handle vast amounts of external knowledge
- If you need to personalize the model's understanding using graph-based algorithms for more relevant document recall
Avoid when
- If your application does not require continuous integration of external documents or personalized information retrieval
- For simpler applications where standard RAG frameworks without KG Personalized PageRank suffice for performance requirements
Observed Jul 14, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Very active (3d since push)
- As of 3w
- Provenance
- Not a fork · Organization account
- As of 3w
- Security (OSV)
- 124 low (124 low)
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install HippoRAGSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
A novel RAG (Retrieval-Augmented Generation) system inspired by human long-term memory that allows language models to learn and recall information from external sources. The project integrates Knowledge Graphs and Personalized PageRank algorithms into the model's retrieval processes.
Capability facts
- Languages
- python
Source: github.language · Aug 1, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 1, 2026)
export OPENAI_API_KEY=<your openai api key> # if you want to use OpenAI modelSource link
Source: README excerpt (regex_v1, Aug 1, 2026)
Use Conda or `uv` to create a Python 3.10 environment. A project-local `.venv` is recommended for development.Source link
Tags
README
Installation
Use Conda or uv to create a Python 3.10 environment. A project-local .venv is recommended for development.
conda create -n hipporag python=3.10
conda activate hipporag
pip install hipporag
Set only the environment variables required by the models you use:
export CUDA_VISIBLE_DEVICES=0,1,2,3
export HF_HOME=<path to Huggingface home directory>
export OPENAI_API_KEY=<your openai api key> # if you want to use OpenAI model
conda activate hipporag
For a project-local environment managed by uv:
uv venv --python 3.10 .venv
source .venv/bin/activate
uv pip install -e .
Local Deployment (vLLM)
This simple example will illustrate how to use hipporag with any vLLM-compatible locally deployed LLM.
- Run a local OpenAI-compatible vLLM server with specified GPUs (make sure you leave enough memory for your embedding model).
Keep VLLM_WORKER_MULTIPROC_METHOD=spawn when running vLLM with multiple GPUs; it makes the required multiprocessing mode explicit and avoids CUDA initialization problems with forked workers.
export CUDA_VISIBLE_DEVICES=0,1
export VLLM_WORKER_MULTIPROC_METHOD=spawn
export HF_HOME=<path to Huggingface home directory>
conda activate hipporag # vllm should be in this environment
For agents
This page has a .md twin and JSON over the API.