Using the NVIDIA API Catalog

Example Features

This example deploys a developer RAG pipeline for chat Q&A and serves inferencing from an NVIDIA API Catalog endpoint instead of NVIDIA Triton Inference Server, a local Llama 2 model, or local GPUs.

Developers get free credits for 10K requests to any of the available models.

Model	Embedding	Framework	Description	Multi-GPU	TRT-LLM	Model Location	Triton	Vector Database
ai-mixtral-8x7b-instruct	nvolveqa_40k	Langchain	QA chatbot	NO	NO	API Catalog	NO	Milvus

The following figure shows the sample topology:

The sample chat bot web application communicates with the chain server. The chain server sends inference requests to an NVIDIA API Catalog endpoint.
Optionally, you can deploy NVIDIA Riva. Riva can use automatic speech recognition to transcribe your questions and use text-to-speech to speak the answers aloud.

Using NVIDIA API Catalog endpoints for inference instead of local components.

Prerequisites

Clone the Generative AI examples Git repository using Git LFS:

$ sudo apt -y install git-lfs
$ git clone git@github.com:NVIDIA/GenerativeAIExamples.git
$ cd GenerativeAIExamples/
$ git lfs pull

Install Docker Engine and Docker Compose. Refer to the instructions for Ubuntu.
Optional: Enable NVIDIA Riva automatic speech recognition (ASR) and text to speech (TTS).
- To launch a Riva server locally, refer to the Riva Quick Start Guide.
  - In the provided config.sh script, set service_enabled_asr=true and service_enabled_tts=true, and select the desired ASR and TTS languages by adding the appropriate language codes to asr_language_code and tts_language_code.
  - After the server is running, assign its IP address (or hostname) and port (50051 by default) to RIVA_API_URI in deploy/compose/compose.env.
- Alternatively, you can use a hosted Riva API endpoint. You might need to obtain an API key and/or Function ID for access.
  
  In deploy/compose/compose.env, make the following assignments as necessary:
```
export RIVA_API_URI="<riva-api-address/hostname>:<port>"
export RIVA_API_KEY="<riva-api-key>"
export RIVA_FUNCTION_ID="<riva-function-id>"
```

Get an API Key for the Mixtral 8x7B Instruct API Endpoint

Perform the following steps if you do not already have an API key. You can use different model API endpoints with the same API key.

Navigate to https://build.nvidia.com/explore/discover.
Find the Mixtral 8x7B Instruct card and click the card.
Click Get API Key.
Click Generate Key.
Click Copy Key and then save the API key. The key begins with the letters nvapi-.

Build and Start the Containers

In the Generative AI examples repository, export this variable in terminal.

Add the API key for the model endpoint:
```
export NVIDIA_API_KEY="nvapi-<...>"
```

From the root of the repository, build the containers:

$ docker compose --env-file deploy/compose/compose.env -f deploy/compose/rag-app-api-catalog-text-chatbot.yaml build

Start the containers:

$ docker compose --env-file deploy/compose/compose.env -f deploy/compose/rag-app-api-catalog-text-chatbot.yaml up -d

Example Output

 ✔ Network nvidia-rag         Created
 ✔ Container chain-server     Started
 ✔ Container rag-playground   Started

Start the Milvus vector database:

$ docker compose --env-file deploy/compose/compose.env -f deploy/compose/docker-compose-vectordb.yaml up -d milvus

Example Output

✔ Container milvus-minio       Started
✔ Container milvus-etcd        Started
✔ Container milvus-standalone  Started

Confirm the containers are running:

$ docker ps --format "table {{.ID}}\t{{.Names}}\t{{.Status}}"

Example Output

CONTAINER ID   NAMES               STATUS
39a8524829da   rag-playground      Up 2 minutes
bfbd0193dbd2   chain-server        Up 2 minutes
ec02ff3cc58b   milvus-standalone   Up 3 minutes
6969cf5b4342   milvus-minio        Up 3 minutes (healthy)
57a068d62fbb   milvus-etcd         Up 3 minutes (healthy)

Next Steps

Access the web interface for the chat server. Refer to Using the Sample Chat Web Application for information about using the web interface.
Configuring an Alternative Vector Database
Stop the containers by running docker compose -f deploy/compose/rag-app-api-catalog-text-chatbot.yaml down and docker compose -f deploy/compose/docker-compose-vectordb.yaml down.