DOC: Add guide for building RAG applications with Mastra and ChromaDB

[akuya-ekorot]

Description of changes

This pull request introduces a new guide to the documentation demonstrating how to build a Retrieval-Augmented Generation (RAG) application using ChromaDB as the vector store within the Mastra framework.

The guide provides a step-by-step walkthrough covering:

• Setting up a local ChromaDB instance.
• Initializing a Mastra project.
• Configuring Mastra to connect to ChromaDB using @mastra/chroma.
• Creating custom API endpoints in Mastra (using Hono) for:
  • Processing text documents (chunking with @mastra/rag).
  • Generating embeddings using Cohere via the AI SDK (@ai-sdk/cohere, ai).
  • Upserting embeddings and metadata into a ChromaDB collection.
  • Querying the ChromaDB collection based on semantic similarity.
• Running and testing the complete RAG workflow.

Type of Change

• New documentation content

[github-actions]

Reviewer Checklist

Please leverage this checklist to ensure your code review is thorough before approving

Testing, Bugs, Errors, Logs, Documentation

• Can you think of any use case in which the code does not behave as intended? Have they been tested?
• Can you think of any inputs or external events that could break the code? Is user input validated and safe? Have they been tested?
• If appropriate, are there adequate property based tests?
• If appropriate, are there adequate unit tests?
• Should any logging, debugging, tracing information be added or removed?
• Are error messages user-friendly?
• Have all documentation changes needed been made?
• Have all non-obvious changes been commented?

System Compatibility

• Are there any potential impacts on other parts of the system or backward compatibility?
• Does this change intersect with any items on our roadmap, and if so, is there a plan for fitting them together?

Quality

• Is this code of a unexpectedly high quality (Readability, Modularity, Intuitiveness)