Signed-off-by: chensuyue <suyue.chen@intel.com>
Generative AI Examples
This project provides a collective list of Generative AI (GenAI) and Retrieval-Augmented Generation (RAG) examples such as chatbot with question and answering (ChatQnA), code generation (CodeGen), document summary (DocSum), etc.
GenAI Examples
All the examples are well-validated on Intel platforms. In addition, these examples are:
-
Easy to use. Use ecosystem-compliant APIs to build the end-to-end GenAI examples
-
Easy to customize. Customize the example using different framework, LLM, embedding, serving etc.
-
Easy to deploy. Deploy the GenAI examples with performance on Intel platforms
Note
: The below support matrix gives the validated configurations. Feel free to customize per your needs.
ChatQnA
ChatQnA is an example of chatbot for question and answering through retrieval argumented generation (RAG).
| Framework | LLM | Embedding | Vector Database | Serving | HW | Description |
| LangChain | NeuralChat-7B | BGE-Base | Redis | TGI TEI | Xeon/Gaudi2 | Chatbot |
| LangChain | NeuralChat-7B | BGE-Base | Chroma | TGI TEI | Xeon/Gaudi2 | Chatbot |
| LangChain | Mistral-7B | BGE-Base | Redis | TGI TEI | Xeon/Gaudi2 | Chatbot |
| LangChain | Mistral-7B | BGE-Base | Qdrant | TGI TEI | Xeon/Gaudi2 | Chatbot |
CodeGen
CodeGen is an example of copilot designed for code generation in Visual Studio Code.
| Framework | LLM | Serving | HW | Description |
| LangChain | meta-llama/CodeLlama-7b-hf | TGI | Xeon/Gaudi2 | Copilot |
CodeTrans
CodeTrans is an example of chatbot for converting code written in one programming language to another programming language while maintaining the same functionality.
| Framework | LLM | Serving | HW | Description |
| LangChain | HuggingFaceH4/mistral-7b-grok | TGI | Xeon/Gaudi2 | Code Translation |
DocSum
DocSum is an example of chatbot for summarizing the content of documents or reports.
| Framework | LLM | Serving | HW | Description |
| LangChain | NeuralChat-7B | TGI | Xeon/Gaudi2 | Chatbot |
| LangChain | Mistral-7B | TGI | Xeon/Gaudi2 | Chatbot |