filegraphdb 0.1.1

A local file-native graph layer for relationship-aware text retrieval.

FileGraphDB

FileGraphDB builds a local relationship graph over ordinary text files so an LLM can retrieve only the most relevant files instead of reading an entire folder.

Setup

python -m venv .venv
.\.venv\Scripts\Activate.ps1
pip install -r requirements.txt
pip install -e .

Build A File Graph

filegraph --folder . build

Files longer than 2,000 words keep their file node and are also split into overlapping chunk nodes:

big_report.txt
big_report.txt#chunk-0001
big_report.txt#chunk-0002

The graph can contain:

File --CONTAINS--> Chunk
File --SEMANTICALLY_SIMILAR--> File
Chunk --SEMANTICALLY_SIMILAR--> Chunk
File/Chunk --SHARES_ENTITY--> File/Chunk
File/Chunk --SHARES_TOPIC--> File/Chunk

You can tune this:

filegraph --folder ./docs build --chunk-threshold 2000 --chunk-words 800 --chunk-overlap 120

Or disable chunking:

filegraph --folder ./docs --chunk-threshold 0 build

Show strongest relationships:

filegraph --folder . edges

Find files related to one file:

filegraph --folder . related research/file_native_graph_database.md

Retrieve likely files for an LLM query:

filegraph --folder . search "How can file relationships reduce LLM token cost?"

Print LLM-ready context:

filegraph --folder . context "How can file relationships reduce LLM token cost?"

Python Library

from filegraphdb import FileGraphDB

graph = FileGraphDB("./docs")
graph.build()

for result in graph.retrieve("What caused the project delay?", limit=4):
    print(result.document.rel_path, result.score)

The first build is the expensive step. After that, the SQLite graph lives at:

.filegraphdb.sqlite

Optional Open-Source Embedding Model

By default, FileGraphDB uses local TF-IDF + LSA semantic vectors from scikit-learn. To use a stronger open-source embedding model:

pip install -e ".[models]"
filegraph --folder ./docs --use-model build

The default model is:

sentence-transformers/all-MiniLM-L6-v2

Small LLM Demo

The earlier local LLM demo is still available:

python small_llm.py