mirror of
https://github.com/hwchase17/langchain
synced 2024-11-02 09:40:22 +00:00
e6240fecab
- **Description:** Adds a RAG template that uses NVIDIA AI playground and embedding models, along with Milvus vector store - **Dependencies:** This template depends on the AI playground service in NVIDIA NGC. API keys with a significant trial compute are available (10k queries at the time of writing). This template also depends on the Milvus Vector store which is publicly available. Note: [A quick link to get a key](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-foundation/models/codellama-13b/api) when you have an NGC account. Generate Key button at the top right of the code window. --------- Co-authored-by: Sagar B Manjunath <sbogadimanju@nvidia.com> Co-authored-by: Erick Friis <erick@langchain.dev> |
||
---|---|---|
.. | ||
__init__.py |