TrustGraph deploys a full E2E (end-to-end) AI solution with native GraphRAG in minutes. TrustGraph is designed for maximum flexibility and modularity whether it's calling Cloud LLMs or deploying SLMs On-Device. TrustGraph ingests data to build a RDF style knowledge graph to enable accurate and private `RAG` responses using only the knowledge you want, when you want.
The pipeline processing components are interconnected with a pub/sub engine to maximize modularity for agent integration. The core processing components decode documents, chunk text, perform embeddings, apply an On-Device SLM/LLM, call a LLM API, and generate LM predictions.
The processing showcases the reliability and efficiences of GraphRAG algorithms which can capture contextual language flags that are missed in conventional RAG approaches. Graph querying algorithms enable retrieving not just relevant knowledge but language cues essential to understanding semantic uses unique to a text corpus.
TrustGraph is designed to be modular to support as many Language Models and environments as possible. A natural fit for a modular architecture is to decompose functions into a set modules connected through a pub/sub backbone. [Apache Pulsar](https://github.com/apache/pulsar/) serves as this pub/sub backbone. Pulsar acts as the data broker managing inputs and outputs between modules.
- For processing flows, Pulsar accepts the output of a processing module and queues it for input to the next subscribed module.
- For services such as LLMs and embeddings, Pulsar provides a client/server model. A Pulsar queue is used as the input to the service. When processed, the output is then delivered to a separate queue where a client subscriber can request that output.
The entire architecture, the pub/sub backbone and set of modules, is bundled into a single Python package. A container image with the package installed can also run the entire architecture.
-`kg-extract-definitions` - knowledge extractor - examines text and produces graph edges. describing discovered terms and also their defintions. Definitions are derived using the input documents.
-`pdf-decoder` - Takes a PDF doc and emits text extracted from the document. Text extraction from PDF is not a perfect science as PDF is a printable format. For instance, the wrapping of text between lines in a PDF document is not semantically encoded, so the decoder will see wrapped lines as space-separated.
-`ge-write-qdrant` - Takes graph embeddings mappings and records them in the vector embeddings store.
