apunkt/trustgraph
1
0
Fork 0
mirror of https://github.com/trustgraph-ai/trustgraph.git synced 2026-04-25 00:16:23 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Merge branch 'master' into release/v1.0

Browse source
This commit is contained in:
Cyber MacGeddon 2025-07-03 16:01:40 +01:00
commit fac42eb01b
1 changed files with 18 additions and 138 deletions
Download patch file Download diff file Expand all files Collapse all files

156
README.md
View file

@ -37,40 +37,20 @@ Take control of your data and AI future with **TrustGraph**. Universal connector
## Why TrustGraph? ## Why TrustGraph?
Deploying truly intelligent and reliable AI agents is challenging. Many platforms are opaque, offer limited control, or rely on simplistic knowledge retrieval that falls short for complex or large datasets. TrustGraph provides a robust, open-source alternative, empowering you to build AI agents that are: If you want to build powerful, intelligent AI applications without getting bogged down by complex infrastructure, brittle data pipelines, or opaque "black box" systems, TrustGraph is the platform that accelerates your AI transformation by solving these core problems.
1. **Grounded in Deep, Interconnected Knowledge (Superior GraphRAG):** - **Go Beyond Basic RAG with GraphRAG**: Stop building agents that just retrieve text snippets. TrustGraph provides the tooling to automatically build and query Knowledge Graphs combined with Vector Embeddings, enabling you to create applications with deep contextual reasoning and higher accuracy.
* **Go Beyond Basic RAG:** TrustGraph excels at building and leveraging sophisticated **Knowledge Graphs combined with Vector Embeddings** (our "Knowledge Packages"). This allows your agents to access and reason over rich, interconnected information and its explicit relationships, not just semantically similar text fragments. - **Decouple Your App from the AI Stack**: Our modular, containerized architecture lets you deploy anywhere (Docker, K8s, bare-metal) and swap out components (LLMs, vector DBs, graph DBs) without re-architecting your core application. Write your app once, knowing the underlying AI stack can evolve.
* **Reduced Hallucinations, Higher Accuracy:** Provide your agents with contextually rich information, leading to more accurate, reliable, and trustworthy responses. - **Automate the Knowledge Pipeline**: Focus on building your application's logic, not on writing ETL scripts for AI. TrustGraph provides a unified platform to ingest data from silos, transform it into structured Knowledge Packages, and deliver it to your AI – streamlining the entire "knowledge supply chain."
- **Enjoy Full Transparency & Control**: As an open-source platform, you get complete visibility into the system's inner workings. Debug more effectively, customize components to your needs, and maintain total control over your application's data flow and security, eliminating vendor lock-in.
2. **Open, Transparent & Controllable:**
* **Escape the Black Box:** As an **open-source platform**, TrustGraph gives you full visibility into its workings. Understand how your data is processed, managed, and utilized by your agents.
* **Full Stack Sovereignty:** Deploy the entire TrustGraph platform – including your sensitive Knowledge Packages – wherever you choose: on-premises, private cloud, public cloud, or even bare metal. You maintain ultimate control over your data and AI stack.
3. **Flexible & Future-Proof:**
* **Modular Architecture:** Easily integrate best-of-breed LLMs (cloud APIs or self-hosted via Ollama, TGI, vLLM, etc.), VectorDBs, and Knowledge Graphs. TrustGraph isn't prescriptive; it's adaptable.
* **Deploy Anywhere:** Our fully containerized architecture (Docker, Kubernetes) ensures your AI agent solutions can be provisioned consistently across any environment.
* **Portable Knowledge Packages:** While tightly integrated, the principles behind our Knowledge Packages are designed for interoperability, giving you more freedom and avoiding deep vendor lock-in for your core data assets.
4. **Designed for AI Native Intelligence Automation:**
* **Automate the Intelligence Supply Chain:** TrustGraph streamlines the end-to-end process of ingesting data, constructing Knowledge Packages, managing them, and delivering that structured knowledge to your AI agents and applications.
* **Build Sophisticated Agents:** Leverage capabilities like customizable Knowledge Graph construction and a ReAct Agent Router to develop agents capable of complex reasoning and tool use.
5. **Cost-Effective & Scalable:**
* **Optimize Your AI Spend:** Choose the most cost-effective LLMs, infrastructure, and storage for your needs without being locked into a single provider's ecosystem.
* **Scale with Confidence:** Designed to handle growing knowledge bases and increasing agent interaction loads.
**In short, choose TrustGraph if you need to build powerful AI agents that are truly intelligent, transparently auditable, fully under your control, and grounded in the rich, interconnected reality of your unique enterprise knowledge.**
## Getting Started ## Getting Started
This is a very-quickstart. See [other installation options](docs/README.md#ways-to-deploy). This is a very-quickstart. See [other installation options](docs/README.md#ways-to-deploy).
- [Configuration Builder](#configuration-builder)
- [Install the CLI](#install-the-trustgraph-cli) - [Install the CLI](#install-the-trustgraph-cli)
- [Configuration Builder](#-configuration-builder)
- [Platform Restarts](#platform-restarts)
- [Test Suite](#test-suite) - [Test Suite](#test-suite)
- [Example Notebooks](#example-trustgraph-notebooks)
### Developer APIs and CLI ### Developer APIs and CLI
@ -79,15 +59,6 @@ This is a very-quickstart. See [other installation options](docs/README.md#ways
- [**Python SDK**](https://trustgraph.ai/docs/api/apistarted) - [**Python SDK**](https://trustgraph.ai/docs/api/apistarted)
- [**TrustGraph CLI**](https://trustgraph.ai/docs/running/cli) - [**TrustGraph CLI**](https://trustgraph.ai/docs/running/cli)
See the [API Developer's Guide](#api-documentation) for more information.
For users, **TrustGraph** has the following interfaces:
- [**Configuration Builder**](#-configuration-builder)
- [**Test Suite**](#test-suite)
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 ### Install the TrustGraph CLI
``` ```
@ -99,46 +70,13 @@ pip3 install trustgraph-cli==<trustgraph-version>
## Configuration Builder ## Configuration Builder
TrustGraph is endlessly customizable by editing the `YAML` resource files. The **Configuration Builder** provides a tool for building a custom configuration that deploys with your selected orchestration method in your target environment. The [**Configuration Builder**](https://config-ui.demo.trustgraph.ai/) assembles all of the selected components and builds them into a deployable package. It has 4 sections:
- [**Configuration Builder**](https://config-ui.demo.trustgraph.ai/) - **Version**: Select the version of TrustGraph you'd like to deploy
The **Configuration Builder** has 5 important sections:
- **TrustGraph Version**: Select the version of TrustGraph you'd like to deploy
- **Component Selection**: Choose from the available deployment platforms, LLMs, graph store, VectorDB, chunking algorithm, chunking parameters, and LLM parameters - **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 - **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 `YAML` files with deployment instructions - **Finish Deployment**: Download the launch `YAML` files 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 ### 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: 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:
@ -149,50 +87,15 @@ If added to the build in the **Configuration Builder**, the **Test Suite** will
- **Graph Visualizer**: Visualize semantic relationships in **3D** - **Graph Visualizer**: Visualize semantic relationships in **3D**
- **Data Loader**: Directly load `.pdf`, `.txt`, or `.md` into the system with document metadata - **Data Loader**: Directly load `.pdf`, `.txt`, or `.md` into the system with document metadata
### Example TrustGraph Notebooks
- [**REST API Notebooks**](https://github.com/trustgraph-ai/example-notebooks/tree/master/api-examples)
- [**Python SDK Notebooks**](https://github.com/trustgraph-ai/example-notebooks/tree/master/api-library)
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-compose`
- `minikube-k8s`
- `gcp-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 Builder` 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](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.
## GraphRAG ## GraphRAG
TrustGraph features an advanced GraphRAG approach that automatically constructs Knowledge Graphs with mapped Vector Embeddings to provide richer and more accurate context to LLMs for trustworthy agents. TrustGraph features an advanced GraphRAG approach that automatically constructs Knowledge Graphs with mapped Vector Embeddings to provide richer and more accurate context to LLMs for trustworthy agents.
**How TrustGraph's GraphRAG Works:** **How TrustGraph's GraphRAG Works:**
1. **Automated Knowledge Graph Construction:** - **Automated Knowledge Graph Construction:** Data Transformation Agents processes source data to automatically **extract key entities, topics, and the relationships** connecting them. Vector emebeddings are then mapped to these semantic relationships for context retrieval.
* TrustGraph processes source data to automatically **extract key entities, topics, and the relationships** connecting them. - **Hybrid Retrieval:** When an agent needs to perform deep research, it first performs a **cosine similarity search** on the vector embeddings to identify potentially relevant concepts and relationships within the knowledge graph. This initial vector search **pinpoints relevant entry points** within the structured Knowledge Graph.
* It then maps these extracted **semantic relationships and concepts to high-dimensional vector embeddings**, capturing the nuanced meaning beyond simple keyword matching. - **Context Generation via Subgraph Traversal:** Based on the ranked results from the similarity search, agents are provided with only the relevant subgraphs for **deep context**. Users can configure the **number of 'hops'** (relationship traversals) to extend the depth of knowledge availabe to the agents. This structured **subgraph**, containing entities and their relationships, forms a highly relevant and context-aware input prompt for the LLM that is endlessly configurable with options for the number of entities, relationships, and overall subgraph size.
2. **Hybrid Retrieval Process:**
* When an agent needs to perform deep research, it first performs a **cosine similarity search** on the vector embeddings to identify potentially relevant concepts and relationships within the knowledge graph.
* This initial vector search **pinpoints relevant entry points** within the structured Knowledge Graph.
3. **Context Generation via Subgraph Traversal:**
* Based on the ranked results from the similarity search, agents are provided with only the relevant subgraphs for **deep context**.
* Users can configure the **number of 'hops'** (relationship traversals) to extend the depth of knowledge availabe to the agents.
* This structured **subgraph**, containing entities and their relationships, forms a highly relevant and context-aware input prompt for the LLM that is endlessly configurable with options for the number of entities, relationships, and overall subgraph size.
## Knowledge Packages ## Knowledge Packages
@ -215,26 +118,13 @@ The platform orchestrates a comprehensive suite of services to transform externa
Within the **TrustGraph** Platform, the services are grouped as follows: Within the **TrustGraph** Platform, the services are grouped as follows:
1. **Data Orchestration:** - **Data Orchestration:** This crucial set of services manages the entire lifecycle of ingesting and preparing data to become AI-ready knowledge. It includes **Data Ingest** capabilities for various data types, a *Data Librarian* for managing and cataloging this information, *Data Transformation* services to clean, structure, and refine raw data, and ultimately produces consumable *Knowledge Packages* – the structured, enriched knowledge artifacts for AI.
* This crucial set of services manages the entire lifecycle of ingesting and preparing data to become AI-ready knowledge. It includes **Data Ingest** capabilities for various data types, a **Data Librarian** for managing and cataloging this information, **Data Transformation** services to clean, structure, and refine raw data, and ultimately produces consumable **Knowledge Packages** – the structured, enriched knowledge artifacts for AI. - **Data Storage:** The platform relies on a flexible storage layer designed to handle the diverse needs of AI applications. This includes dedicated storage for *Knowledge Graphs* (to represent interconnected relationships), *VectorDBs* (for efficient semantic similarity search on embeddings), and *Tabular Datastores* (for structured data).
- **Intelligence Orchestration:** This is the core reasoning engine of the platform. It leverages the structured knowledge from the Storage layer to perform *Deep Knowledge Retrieval* (advanced search and context discovery beyond simple keyword matching) and facilitate *Agentic Thinking*, enabling AI agents to process information and form complex responses or action plans.
2. **Data Storage:** - **Agent Orchestration:** This group of services is dedicated to managing and empowering the AI agents themselves. The *Agent Manager* handles the lifecycle, configuration, and operation of agents, while *Agent Tools* provide a framework or library of capabilities that agents can utilize to perform actions or interact with other systems.
* The platform relies on a flexible storage layer designed to handle the diverse needs of AI applications. This includes dedicated storage for **Knowledge Graphs** (to represent interconnected relationships), **VectorDBs** (for efficient semantic similarity search on embeddings), and **Tabular Datastores** (for structured data). - **Model Orchestration:** This layer is responsible for the deployment, management, and operationalization of the various AI models TrustGraph uses or provides to agents. This includes *LLM Deployment*, *Embeddings Deployment*, and *OCR Deployment*. Crucially, it features *Cross Hardware Support*, indicating the platform's ability to run these models across diverse computing environments.
- **Prompt Management:** Effective interaction with AI, especially LLMs and agents, requires precise instruction. This service centralizes the management of all prompt types: *LLM System Prompts* (to define an LLM's persona or core instructions), *Data Transformation Prompts* (to guide AI in structuring data), **RAG Context** generation (providing relevant intelligence to LLMs), and *Agent Definitions* (the core instructions and goals for AI agents).
3. **Intelligence Orchestration:** - **Platform Services:** These foundational services provide the essential operational backbone for the entire TrustGraph platform, ensuring it runs securely, reliably, and efficiently. This includes *Access Controls* (for security and permissions), *Secrets Management* (for handling sensitive credentials), *Logging* (for audit and diagnostics), *Observability* (for monitoring platform health and performance), *Realtime Cost Observability* (for tracking resource consumption expenses), and *Hardware Resource Management* (for optimizing the use of underlying compute).
* This is the core reasoning engine of the platform. It leverages the structured knowledge from the Storage layer to perform **Deep Knowledge Retrieval** (advanced search and context discovery beyond simple keyword matching) and facilitate **Agentic Thinking**, enabling AI agents to process information and form complex responses or action plans.
4. **Agent Orchestration:**
* This group of services is dedicated to managing and empowering the AI agents themselves. The **Agent Manager** handles the lifecycle, configuration, and operation of agents, while **Agent Tools** provide a framework or library of capabilities that agents can utilize to perform actions or interact with other systems.
5. **Model Orchestration:**
* This layer is responsible for the deployment, management, and operationalization of the various AI models TrustGraph uses or provides to agents. This includes **LLM Deployment**, **Embeddings Deployment**, and **OCR Deployment**. Crucially, it features **Cross Hardware Support**, indicating the platform's ability to run these models across diverse computing environments.
6. **Prompt Management:**
* Effective interaction with AI, especially LLMs and agents, requires precise instruction. This service centralizes the management of all prompt types: **LLM System Prompts** (to define an LLM's persona or core instructions), **Data Transformation Prompts** (to guide AI in structuring data), **RAG Context** generation (providing relevant intelligence to LLMs), and **Agent Definitions** (the core instructions and goals for AI agents).
7. **Platform Services:**
* These foundational services provide the essential operational backbone for the entire TrustGraph platform, ensuring it runs securely, reliably, and efficiently. This includes **Access Controls** (for security and permissions), **Secrets Management** (for handling sensitive credentials), **Logging** (for audit and diagnostics), **Observability** (for monitoring platform health and performance), **Realtime Cost Observability** (for tracking resource consumption expenses), and **Hardware Resource Management** (for optimizing the use of underlying compute).
## Integrations ## Integrations
TrustGraph provides maximum flexibility so your agents are always powered by the latest and greatest components. TrustGraph provides maximum flexibility so your agents are always powered by the latest and greatest components.
@ -316,16 +206,6 @@ TrustGraph provides maximum flexibility so your agents are always powered by the
- For flows, Pulsar accepts the output of a processing module and queues it for input to the next subscribed module. - For 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. - 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 Transformation Agents
TrustGraph transforms data to an ultra-dense knowledge graph using 3 automonous data transformation 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: PDF file:
``` ```
tg-load-pdf <document.pdf> tg-load-pdf <document.pdf>