# Day 14 - Feb 6 2026

Combine LLMs, Vector Databases, RAG, and APIs into a single, cohesive application.

### 1. The Architecture

This project is not a script; it is a System.

* Knowledge Layer: `best_practices.txt` -> ChromaDB (Vector Store).
* Reasoning Layer: Llama 3.2 (Ollama).
* Interface Layer: FastAPI.

### 2. How it Works (The Data Flow)

1. Startup: The app checks if the Vector DB is empty. If so, it loads the "Best Practices" file.
2. Request: User sends a resume snippet via API.
3. RAG Lookup: The system searches the Vector DB for the *most relevant* advice rules.
4. Synthesis: The LLM combines the *User's Resume* + *The Retrieved Rules* to generate a critique.

### 3. Why this is "Production-Grade"

* Scalable: We can add 1,000 more rules to the text file, and the AI gets smarter without changing the code.
* Modular: The database is separate from the logic.
* Standardized: It speaks JSON, so a frontend React app could easily connect to this.

### Status:

* [x] Vector Database Persistence
* [x] RAG Pipeline Integration
* [x] FastAPI Endpoint Creation
* [x] End-to-End Testing


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://shankar-lab.gitbook.io/mylearning/15-days-genai-learning-challenge/day-14-feb-6-2026.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.