added BeyondLLM cookbooks

[shivayapandey]

Description

This PR introduces three new cookbooks that focus on different aspects of evaluation and fine-tuning with Mistral models:

• Evaluation of Mistral Instruct using HuggingFace: Demonstrates how to evaluate the Mistral Instruct model using HuggingFace and BeyondLLM. It sets up a retrieval pipeline, generates responses, and evaluates the model's performance based on context relevancy, answer relevancy, and groundedness metrics.

• Fine Tune Embeddings Advanced RAG: Shows how to fine-tune embeddings using BeyondLLM and build an advanced Retrieval-Augmented Generation (RAG) pipeline with Mistral AI LLM. It includes steps for loading a dataset, fine-tuning an embedding model, setting up a retriever, and generating responses to queries.

• LlamaIndex x Mistral AI x BeyondLLM Evaluation: Integrates LlamaIndex, Mistral AI, and BeyondLLM to evaluate model performance. It sets up a retrieval pipeline, generates responses to queries, and assesses the model's performance using key evaluation metrics.

Dependencies:

• BeyondLLM
• Mistral AI
• HuggingFace

Type of Change

What type of PR is it?

• ✅ New Cookbook
• ✅ Notebook File
  - ✅ Does it work on Google Colab?

Cookbook Checklist:

• My code is easy to read and well structured. ✅
• I've tagged the versions of any dependency required. ✅
• I have performed a self-review of my own code. ✅
• I have commented my code, particularly in hard-to-understand areas. ✅
• My changes generate no new warnings or errors. ✅

README.md Checklist

• I've added my cookbook to the table. ✅