TrustGraph deploys a full E2E (end-to-end) AI solution with native GraphRAG in minutes. Autonomous Knowledge Agents build ultra-dense knowlege graphs to fully capture all knowledge context. 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, create mapped embeddings, generate a RDF knowledge graph, generate AI predictions from either a Cloud LLM or On-Device SLM.
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 fully containerized and is launched with a `YAML` configuration file. Unzipping the `deploy.zip` will add the `deploy` directory with the following subdirectories:
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 of 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 data processing queues connected to procesing 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.
TrustGraph extracts knowledge from a text corpus (PDF or text) to an ultra-dense knowledge graph using 3 automonous knowledge agents. These agents focus on individual elements needed to build the RDF knowledge graph. The agents are:
The agent prompts are built through templates, enabling customized extraction agents for a specific use case. The extraction agents are launched automatically with the loader commands.
