13 KiB
Autonomous Operations Platform
🚀 Getting Started 📺 YouTube 🧠 Knowledge Cores ⚙️ API Docs 🧑💻 CLI Docs 💬 Discord 📖 Blog
TrustGraph transforms agents from experimental concepts into a new paradigm of continuous operations.
The platform provides a robust, scalable, and reliable infrastructure designed for complex environments, complete with a full observability stack. TrustGraph automates the deployment in local and cloud environments of state-of-the-art RAG pipelines using Knowledge Graphs and Vector Databases with a unified interface to all major LLM providers.
Table of Contents
- ✨ Key Features
- 🎯 Why TrustGraph?
- 🚀 Getting Started
- 🔧 Configuration Builder
- 📐 Architecture
- 🧩 Integrations
- 📊 Observability & Telemetry
- 🤝 Contributing
- 📄 License
- 📞 Support & Community
✨ Key Features
- 📄 Data Ingest: Bulk ingest documents such as
.pdf,.txt, and.md - 📃 OCR Pipelines: OCR documents with PDF decode, Tesseract, or Mistral OCR services
- 🪓 Adjustable Chunking: Choose your chunking algorithm and parameters
- 🔁 No-code LLM Integration: Anthropic, AWS Bedrock, AzureAI, AzureOpenAI, Cohere, Google AI Studio, Google VertexAI, Llamafiles, LM Studio, Mistral, Ollama, and OpenAI
- 📖 Automated Knowledge Graph Building: No need for complex ontologies and manual graph building
- 🔢 Knowledge Graph to Vector Embeddings Mappings: Connect knowledge graph enhanced data directly to vector embeddings
- ❔Natural Language Data Retrieval: Automatically perform a semantic similiarity search and subgraph extraction for the context of LLM generative responses
- 🧠 Knowledge Cores: Modular data sets with semantic relationships that can saved and quickly loaded on demand
- 🤖 Agent Manager: 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 Qdrant, Pinecone, or Milvus
- 🎛️ Production-Grade Reliability, scalability, and accuracy
- 🔍 Observability and Telemetry: Get insights into system performance with Prometheus and Grafana
- 🎻 Orchestration: Fully containerized with Docker or Kubernetes
- 🥞 Stack Manager: Control and scale the stack with confidence with Apache Pulsar
- ☁️ Cloud Deployments: AWS, Azure, and Google Cloud
- 🪴 Customizable and Extensible: Tailor for your data and use cases
- 🖥️ Configuration Builder: Build the
YAMLconfiguration with drop down menus and selectable parameters - 🕵️ Test Suite: A simple UI to fully test TrustGraph performance
🎯 Why TrustGraph?
Traditional operations often involve manual intervention, siloed tools, and reactive problem-solving. While AI agents show promise, integrating them into reliable, continuous enterprise workflows presents significant challenges:
- Scalability & Reliability: Standalone agent scripts don't scale or offer the robustness required for business-critical operations.
- Contextual Understanding: Agents need deep, relevant context (often locked in enterprise data) to perform complex tasks effectively. RAG is powerful but complex to set up and manage.
- Integration Hell: Connecting agents to diverse enterprise systems, data sources, and various LLMs is difficult and time-consuming.
- Lack of Oversight: Monitoring, debugging, and understanding the behavior of multiple autonomous agents in production is critical but often overlooked.
TrustGraph addresses these challenges by providing:
- A platform, not just a library, for managing the lifecycle of autonomous operations.
- Automated, best-practice RAG deployments that combine the strengths of semantic vector search and structured knowledge graph traversal.
- A standardized layer for LLM interaction and enterprise system integration.
- Built-in observability to ensure you can trust and manage your autonomous systems.
🚀 Getting Started
Developer APIs and CLI
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 Builder 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.
Install the TrustGraph CLI
pip3 install trustgraph-cli==0.21.17
Note
The
TrustGraph CLIversion must match the desiredTrustGraphrelease version.
🔧 Configuration Builder
TrustGraph is endlessly customizable by editing the YAML launch files. The Configuration Builder provides a quick and intuitive tool for building a custom configuration that deploys with Docker, Podman, Minikube, or Google Cloud. There is a Configuration Builder for the both the lastest and stable TrustGraph releases.
The Configuration Builder 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
- Test Suite 🕵️: Add the Test Suite to the configuration available on port
8888 - Finish Deployment 🚀: Download the launch
YAMLfiles with deployment instructions
The Configuration Builder 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
Platform Restarts
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.
Test Suite
If added to the build in the Configuration Builder, the Test Suite will be available at port 8888. The Test Suite has the following capabilities:
- Graph RAG Chat 💬: Graph RAG queries in a chat interface
- Vector Search 🔎: Semantic similarity search with cosine similarity scores
- Semantic Relationships 🕵️: See semantic relationships in a list structure
- Graph Visualizer 🌐: Visualize semantic relationships in 3D
- Data Loader 📂: Directly load
.pdf,.txt, or.mdinto the system with document metadata
Example TrustGraph Notebooks
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 Builderto build your deployment configuration. Each directory containsYAMLconfiguration 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.
📐 Architecture
TrustGraph removes the biggest headache of building an AI app: connecting and managing all the data, deployments, and models. As a full-stack platform, TrustGraph simplifies the development and deployment of data-driven AI applications. TrustGraph is a complete solution, handling everything from data ingestion to deployment, so you can focus on building innovative AI experiences.
🧩 Integrations
TrustGraph aims to integrate seamlessly with your existing ecosystem.
- LLM Providers: Anthropic, AWS Bedrock, AzureAI, AzureOpenAI, Cohere, Google AI Studio, Google VertexAI, Llamafiles, LM Studio, Mistral, Ollama, and OpenAI
- Vector Databases: Qdrant, Pinecone, and Milvus
- Knowledge Graphs: Memgraph, Neo4j, and FalkorDB
- Data Stores: Apache Cassandra
- Observability: Prometheus and Grafana
Pulsar Workflows
- 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.
Data Extraction Agents
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>
Graph RAG Queries
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?"
Agent Flow
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
-vto the agent request will return all of the agent manager's thoughts and observations that led to the final response.
API Documentation
Developing on TrustGraph using APIs