> ## Documentation Index
> Fetch the complete documentation index at: https://docs.berri.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Improving Document QA w/ Custom Chunking Tutorial

> This tutorial will guide you on how to use your own customized chunking strategy and pass those chunks to BerriAI.

Let's say we want to QA a [research paper](https://drive.google.com/file/d/1g-RBkhExWOsNJ17IBOQmv-4owaV5nH1X/view?usp=share_link).

Since we can't fit the entire paper into GPT, we need a way to break this paper down into smaller chunks. By default Berri provides custom chunking, but we can also write our own.

Writing your own chunking strategy is a good way of improving the quality of our responses (since we're answering user questions based on the most relevant chunk we find).

**Relevant Links:**

1. [Link to code](https://colab.research.google.com/drive/1yxPFyGOzDIkivRbMD62kH3wBU5Zgwo4o?usp=sharing)
2. [Link to playground](https://play.berri.ai/)

# Step 1: Set up your environment

For this tutorial we're going to use a [sample ML research paper](https://drive.google.com/file/d/1g-RBkhExWOsNJ17IBOQmv-4owaV5nH1X/view?usp=share_link) as our initial data source.

```python theme={null}
!pip install gdown
!gdown 1g-RBkhExWOsNJ17IBOQmv-4owaV5nH1X
!pip install PyPDF2
import json
import requests
```

# Step 2: Customize chunking

In this case, let's make every page a chunk (i.e. the thing we feed into GPT).

```python theme={null}
import PyPDF2
text_list = []
with open("./ml_paper.pdf", "rb") as fp:
    # Create a PDF object
    pdf = PyPDF2.PdfReader(fp)

    # Get the number of pages in the PDF document
    num_pages = len(pdf.pages)

    # Iterate over every page
    for page in range(num_pages):
        # Extract the text from the page
        page_text = pdf.pages[page].extract_text()
        text_list.append(page_text) # chunk by page
```

Here we're using our own data loader (PyPDF2), extracting the text from the page, and adding that to `text_list`.

# Step 3: Creating a custom chatGPT instance to QA against our Doc

Since we've stored our chunks as a list (`text_list`), let's pass that to Berri.

```python theme={null}
url = "https://api.berri.ai/create_app"
data = {"user_email": <your_email>, "data_source": json.dumps(text_list)}
response = requests.post(url, data=data)
response.text
```

# Step 4: Testing our instance in playground

Each instance has it's own unique playground link. This is a place for you to test your model and quickly make any changes (e.g. updating prompt, etc.)

```python theme={null}
playground_endpoint = response.json()["playground_endpoint"]
```