LlamaIndex + MistralAI Cookbooks

LlamaIndex is a data framework for LLM-based applications which benefit from context augmentation. LlamaIndex provides the essential abstractions to more easily ingest, structure, and access private or domain-specific data in order to inject these safely and reliably into LLMs for more accurate text generation.

Here developers offer some cookbooks for utilizing LlamaIndex with MistralAI’s LLM’s and Embedding models.

1. RAG.ipynb – Notebook to help you build quick RAG and Retriever Pipeline with Mistral.
2. RouterQueryEngine.ipynb – Notebook to help you to use RouterQueryEngine to route user queries.
3. SubQuestionQueryEngine.ipynb – Notebook to help you to use SubQuestionQueryEngine to answer complex user queries.
4. Agents_Tools.ipynb – Notebook to help you to use FunctionCallingAgent and ReActAgent for using Tools and RAG QueryEngine Tools.
5. Adaptive_RAG.ipynb – Notebook to implement AdapativeRAG paper to route user queries based on query complexity using FunctionCallingAgent with Mistral LLM.

Read related articles:

• Llama 2 in MLPerf Inference