# Day 11 - Feb 3 2026

Build an end-to-end pipeline that takes raw files, processes them, and allows for Q\&A interaction.

### 1. The Ingestion Pipeline

Building a RAG app isn't just about the chat; it's about the Data Pipeline.

1. Load: Reading the raw text file (`.txt`).
2. Chunk: Splitting the text into smaller pieces.
3. Embed: Converting those pieces into vectors.
4. Store: Saving them in ChromaDB.

### 2. Why Chunking Matters

You cannot feed a 100-page book into an LLM at once (it exceeds the Context Window).

* My Solution: I implemented a "Paragraph Splitter" (`text.split('\n\n')`).
* The Logic: By breaking the document into logical paragraphs, we ensure that when the Vector DB retrieves a result, it pulls a complete thought, not just a random sentence fragment.

### 3. The "Grounding" Effect

This project proves the concept of Grounding.

* Without Grounding: The AI hallucinates or gives generic advice.
* With Grounding: The AI says, *"According to the context you provided..."* This is the difference between a "Chatbot" and a "Knowledge Assistant."

### Status:

* [x] File Reader Implemented
* [x] Text Chunking Logic Added
* [x] Persistent Vector Storage
* [x] Interactive Q\&A Loop


---

# 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-11-feb-3-2026.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.