***Data Silos:** Connecting to and managing data from various sources (databases, APIs, files) is a nightmare.
***LLM Integration:** Choosing, integrating, and managing different LLMs adds another layer of complexity.
***Deployment Headaches:** Deploying, scaling, and monitoring your AI application is a constant challenge.
***Knowledge Graph Construction:** Taking raw knowledge and structuring it so it can be efficiently retrieved.
***Vector Database Juggling:** Setting up and optimizing a vector database for efficient data retrieval is crucial but complex.
***Data Pipelines:** Building robust ETL pipelines to prepare and transform your data is time-consuming.
***Data Management:** As your app grows, so does the data meaning storage and retreival becomes much more complex.
***Prompt Engineering:** Building, testing, and deploying prompts for specific use cases.
***Reliability:** With every new connection, the complexity ramps up meaning any simple error can bring the entire system crashing down.
## What is TrustGraph?
**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.
## The Stack Layers
- 📄 **Data Ingest**: Bulk ingest documents such as `.pdf`,`.txt`, and `.md`
- ❔**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
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.
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` 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:
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:
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:
TrustGraph `YAML` files are available [here](https://github.com/trustgraph-ai/trustgraph/releases). Download `deploy.zip` for the desired release version.
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:
> 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.
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.
- 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:
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.
