TrustGraph empowers you to deploy reasoning AI Agents in minutes. Our Agentic Graph RAG platform allows you to leverage modular cognitive cores for complex reasoning and information retrieval, all within a scalable and reliable infrastructure. Forget lengthy development cycles – TrustGraph delivers instant reasoning.
- 📄 Document Extraction: Bulk ingest documents such as
.pdf,.txt, and.md - 🪓 Adjustable Chunking: Choose your chunking algorithm and parameters
- 🔁 No-code LLM Integration: Anthropic, AWS Bedrock, AzureAI, AzureOpenAI, Cohere, Google AI Studio, Google VertexAI, Llamafiles, Ollama, and OpenAI
- 📖 Entity, Topic, and Relationship Knowledge Graphs
- 🔢 Mapped Vector Embeddings
- ❔No-code Graph RAG Queries: Automatically perform a semantic similiarity search and subgraph extraction for the context of LLM generative responses
- 🧠 Cognitive Cores: Modular data sets with semantic relationships that can saved and quickly loaded on demand
- 🤖 Agent Flow: Define custom tools used by a ReAct style Agent Manager that fully controls the response flow including the ability to perform Graph RAG requests
- 📚 Multiple Knowledge Graph Options: Full integration with Memgraph, FalkorDB, Neo4j, or Cassandra
- 🧮 Multiple VectorDB Options: Full integration with Pinecone, Qdrant, or Milvus
- 🎛️ Production-Grade reliability, scalability, and accuracy
- 🔍 Observability: get insights into system performance with Prometheus and Grafana
- 🪴 Customizable and Extensible: Tailor for your data and use cases
- 🖥️ Configuration Portal: Build the
YAMLconfiguration with drop down menus and selectable parameters - 🕵️ Data Workbench: Explore your data with a 3D semantic visualizer
See the API Developer's Guide for more information.
For users, TrustGraph has the following interfaces:
The TrustGraph CLI installs the commands for interacting with TrustGraph while running along with the Python SDK. The Configuration Portal enables customization of TrustGraph deployments prior to launching. The REST API can be accessed through port 8088 of the TrustGraph host machine with JSON request and response bodies.
pip3 install trustgraph-cli==0.20.9
Note
The TrustGraph CLI version must match the desired TrustGraph release version.
TrustGraph is endlessly customizable by editing the YAML launch files. The Configuration Portal provides a quick and intuitive tool for building a custom configuration that deploys with Docker, Podman, Minikube, or Google Cloud. There is a Configuration Portal for the both the lastest and stable TrustGraph releases.
The Configuration Portal has 4 important sections:
- Component Selection ✅: Choose from the available deployment platforms, LLMs, graph store, VectorDB, chunking algorithm, chunking parameters, and LLM parameters
- Customization 🧰: Customize the prompts for the LLM System, Data Extraction Agents, and Agent Flow
- Data Workbench 🕵️: Add the Data Workbench to the configuration available on port
8888 - Finish Deployment 🚀: Download the launch
YAMLfiles with deployment instructions
The Configuration Portal will generate the YAML files in deploy.zip. Once deploy.zip has been downloaded and unzipped, launching TrustGraph is as simple as navigating to the deploy directory and running:
docker compose up -d
Tip
Docker is the recommended container orchestration platform for first getting started with TrustGraph.
When finished, shutting down TrustGraph is as simple as:
docker compose down -v
The -v flag will destroy all data on shut down. To restart the system, it's necessary to keep the volumes. To keep the volumes, shut down without the -v flag:
docker compose down
With the volumes preserved, restarting the system is as simple as:
docker compose up -d
All data previously in TrustGraph will be saved and usable on restart.
If added to the build in the Configuration Portal, the Data Workbench will be available at port 8888. The Data Workbench has 4 capabilities:
- System Chat 💬: Graph RAG queries in a chat interface
- Data Explorer 🕵️: See semantic relationships in a list structure
- Data Visualizer 🌐: Visualize semantic relationships in 3D
- Data Loader 📂: Directly load
.pdf,.txt, or.mdinto the system
TrustGraph YAML files are available here. Download deploy.zip for the desired release version.
| Release Type | Release Version |
|---|---|
| Latest | 0.20.9 |
| Stable | 0.20.9 |
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:
docker-composeminikube-k8sgcp-k8s
Note
As more integrations have been added, the number of possible combinations of configurations has become quite large. It is recommended to use the Configuration Portal to build your deployment configuration. Each directory contains YAML configuration files for the default component selections.
Docker:
docker compose -f <launch-file.yaml> up -d
Kubernetes:
kubectl apply -f <launch-file.yaml>
TrustGraph is designed to be modular to support as many LLMs 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 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 documents to an ultra-dense knowledge graph using 3 automonous data extraction agents. These agents focus on individual elements needed to build the knowledge graph. The agents are:
- Topic Extraction Agent
- Entity Extraction Agent
- Relationship Extraction Agent
The agent prompts are built through templates, enabling customized data extraction agents for a specific use case. The data extraction agents are launched automatically with the loader commands.
PDF file:
tg-load-pdf <document.pdf>
Text or Markdown file:
tg-load-text <document.txt>
Once the knowledge graph and embeddings have been built or a cognitive core has been loaded, RAG queries are launched with a single line:
tg-invoke-graph-rag -q "What are the top 3 takeaways from the document?"
Invoking the Agent Flow will use a ReAct style approach the combines Graph RAG and text completion requests to think through a problem solution.
tg-invoke-agent -v -q "Write a blog post on the top 3 takeaways from the document."
Tip
Adding -v to the agent request will return all of the agent manager's thoughts and observations that led to the final response.