llama-index embeddings nvidia integration
Project description
NVIDIA's Embeddings connector
With this connector, you'll be able to connect to and generate from compatible models available as hosted NVIDIA NIMs, such as:
- NVIDIA's Retrieval QA Embedding Model embed-qa-4
First, get a free API key. Go to https://build.nvidia.com, select a model, click "Get API Key".
Store this key in your environment as NVIDIA_API_KEY.
Installation
pip install llama-index-embeddings-nvidia
Usage
from llama_index.embeddings.nvidia import NVIDIAEmbedding
embedder = NVIDIAEmbedding()
embedder.get_query_embedding("What's the weather like in Komchatka?")
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Close
Hashes for llama_index_embeddings_nvidia-0.1.3.tar.gz
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | dae09167e56aacce7ddf79dd1ceec601a39010eda0696c47141979a67809be24 |
|
| MD5 | 207903c4ecda8b18be81c2a9a780ca4e |
|
| BLAKE2b-256 | 8caca398ed8336be13f3b00b0983889c4dcb2a99012acc307883663350113e22 |
Close
Hashes for llama_index_embeddings_nvidia-0.1.3-py3-none-any.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 14f7bc772727d8fbfc95466322f49458336c9fd5729115d8f7ce2ae0596e60f1 |
|
| MD5 | 7dc7adb53239a402c6f0e264e43557f7 |
|
| BLAKE2b-256 | ec56af5f14feb7bbec27ee73274c7d1f00d55484679c178047c35b496a6dc187 |
