apunkt/trustgraph
1
0
Fork 0
mirror of https://github.com/trustgraph-ai/trustgraph.git synced 2026-05-22 22:05:13 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Update README.md for the new Config UI

Browse source
This commit is contained in:
Jack Colquitt 2024-11-10 18:29:44 -08:00 • committed by GitHub
parent ceb6a5ec35
commit 8aa11589f2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 11 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

19
README.md
View file

@ -20,6 +20,7 @@ TrustGraph is a full AI powered data engineering platform. Extract your document
## Key Features ## Key Features
- 📄 **Document Extraction**: Bulk ingest documents such as `.pdf`,`.txt`, and `.md` - 📄 **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 - 🔁 **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** - 📖 **Entity, Topic, and Relationship Knowledge Graphs**
- 🔢 **Mapped Vector Embeddings** - 🔢 **Mapped Vector Embeddings**
@ -49,27 +50,29 @@ pip3 install trustgraph-cli==0.14.15
> [!NOTE] > [!NOTE]
> The `TrustGraph CLI` version must match the desired `TrustGraph` release version. > The `TrustGraph CLI` version must match the desired `TrustGraph` release version.
The full CLI docs are [here](https://trustgraph.ai/docs/running/cli).
### Configuration UI ### Configuration UI
While TrustGraph is endlessly customizable through the `YAML` launch files, the `Configuration UI` can build a custom configuration in seconds that deploys with Docker, Podman, Minikube, or Google Cloud. While TrustGraph is endlessly customizable through the `YAML` launch files, the `Configuration UI` can build a custom configuration in seconds that deploys with Docker, Podman, Minikube, or Google Cloud.
[Configuration UI 🚀](https://config-ui.demo.trustgraph.ai/) [Configuration UI 🚀](https://config-ui.demo.trustgraph.ai/)
https://github.com/user-attachments/assets/90eeaea6-82b7-480a-9972-edb66ea99738 The `Configuration UI` has three sections:
Launch Steps: - **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 data extraction agents
- **Finish Deployment** 🚀: Download the launch `YAML` files with deployment instructions
- For the selected `Model Deployment`, follow the instructions in `Model credentials` section to configure any required environment variables or paths The `Configuration UI` 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:
- Fill in the desired LLM name in the `Model Name` field that corresponds to your selected `Model Deployment`
- Set all desired `Model Parameters`
- Click `GENERATE` under the `Deployment configuration` section
- Follow the instructions under `Launch`
Once `deploy.zip` has been unzipped, launching TrustGraph is as simple as navigating to the `deploy` directory and running:
``` ```
docker compose up -d 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: When finished, shutting down TrustGraph is as simple as:
``` ```
docker compose down -v docker compose down -v