📄 Document RAG Chat

SLM PDF Chat

Securely parses complex PDF documents. Assembles layouts, reads tables, and lets you chat with local legal contracts, research articles, or receipts.

🚀 Overview & Capabilities

Securely parses complex PDF documents. Assembles layouts, reads tables, and lets you chat with local legal contracts, research articles, or receipts.

Key Features

Locally extracts layout text and multi-column paragraphs
Parses database tables inside PDFs directly to list-of-dicts
Built-in RAG chunk generator for offline querying
Supports scanned image PDFs via local OCR integration

💻 Installation

Install the local CPU-optimized package using pip:

Terminal

              # Install local CPU-optimized package
pip install slm-pdf
            

🐙 Checkout from GitHub

Clone only this agent's folder from the monorepo using Git sparse-checkout — no need to download the full repository:

Option 1 — Sparse Checkout (Recommended)

Terminal — Git Sparse Checkout

              # 1. Create and enter a new directory
$ mkdir slm_pdf && cd slm_pdf

# 2. Initialise empty git repo and add remote
$ git init
$ git remote add origin https://github.com/t00114218-stack/SLMAgents.git

# 3. Enable sparse-checkout and set target folder
$ git sparse-checkout init --cone
$ git sparse-checkout set slm_pdf

# 4. Pull only that agent's source
$ git pull origin main
            

Option 2 — Full Repository Clone

Terminal — Full Clone

              $ git clone https://github.com/t00114218-stack/SLMAgents.git
$ cd SLMAgents/slm_pdf
            

💡 Tip: After checkout, install the package locally with pip install -e ./slm_pdf to run in editable mode without publishing to PyPI.

⚙️ Configuration API

Constructor Parameters

Instantiate SLMPDFChat with performance options:

Parameter	Type / Default	Description
model_path	str \| None	Explicit path to ONNX model weights. If omitted, downloads standard checkpoints.
cache_dir	str \| None	Directory to store model weights offline. Defaults to `~/.cache/slm-pdf/`. Also settable via SLM_PDF_CHAT_CACHE_DIR.
n_threads	int \| 4	CPU thread count for ONNX inference. Optimize for CPU core count. Also settable via SLM_PDF_CHAT_N_THREADS.

Methods

Method Signature	Return Type	Description
`load(pdf_path)`	`None`	Saves document configurations locally and performs text extraction mappings.
`ask(question, system_prompt=None, user_input=None)`	`str`	Executes vector search on the document text chunks to synthesize local responses.

Method Parameters (Execution Customization)

All main execution methods accept optional system routing parameters:

Parameter	Type / Default	Description
system_prompt	str \| None	Optional custom system prompt instruction to override the default system template response parameters.
user_input	str \| None	Optional additional user-supplied target text variables or contextual keys.

Quick Start

from slm_pdf import SLMPDFChat

pdf = SLMPDFChat()
pdf.load("invoice.pdf")
ans = pdf.ask(
    "What is the total due amount?",
    system_prompt="Answer format: $XX.XX",
    user_input="Extract tax detail explicitly"
)
print(ans)

Environment Variables

Configure agent parameters globally using environment values:

Environment Variable	Default	Purpose
SLM_PDF_CHAT_N_THREADS	4	Sets CPU inference execution threads.
SLM_PDF_CHAT_CACHE_DIR	~/.cache/slm-pdf/	Default directory to store downloaded ONNX weights.

CPU Performance Tuning

To run the SLMPDFChat engine efficiently on CPU under 1.5 GB memory footprint:

Match Threads to Core Count: Set n_threads or SLM_PDF_CHAT_N_THREADS to match the physical CPU core count.
Sequential Processing: Avoid concurrent processing when batch files are large.
Garbage Collection: Clear variables and run gc.collect() to release model RAM blocks after execution.

Verified Input & Output Logs

Diagnostic execution console response running locally on CPU:

→ INPUT (Ask before load):
"What is total revenue?"

← OUTPUT:
"No PDF document loaded. Please call `.load(pdf_path)` first."