PDF assistant using popular AI
Project description
📚 Malama PDFMAN
Malama PDFMAN is a flexible and extensible framework for querying content from PDF files using various large language models (LLMs) like OpenAI, Gemini, Claude, Mistral, LLaMA, DeepSeek, and more.
🔍 Upload a PDF → Load context → Ask questions → Get intelligent answers from the LLM of your choice.
✨ Features
- ✅ Extracts context from PDFs (fully or within specified page ranges)
- 🤖 Supports multiple LLMs via simple abstraction
- 🔌 Easily pluggable support for new AI providers
- 🧠 Unified prompt structure and clean output handling
- ⚙️ Minimal external dependencies
🏗️ Supported Models
| Provider | Model Examples |
|---|---|
| OpenAI | gpt-3.5-turbo |
| Gemini | gemini-1.5-pro-002 |
| Anthropic | claude-3-7-sonnet-20250219 |
| Groq | compound-beta-mini,llama3-70b-8192 |
| Mistral | mistral-medium |
| Cohere | command-r-plus |
| DeepSeek | deepseek-ai/DeepSeek-R1 |
| Together.ai | Qwen/Qwen2-72B-Instruct |
| Together.ai | Coming Soon - Falcon |
| Amazon Titan | Coming Soon (via Boto3) |
📦 Installation
pip install malama
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file malama-0.1.5.tar.gz.
File metadata
- Download URL: malama-0.1.5.tar.gz
- Upload date:
- Size: 7.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b43ee84538801ba02e7b56ec20a876e92e1dfd6198bbeb54dcab9043cdc678fe
|
|
| MD5 |
07d75c6f8506985c5f5c83d2a085aa33
|
|
| BLAKE2b-256 |
05bf5de55405165550c04531341b6a048b649b5dbe66394c870e6702523fc9cc
|
File details
Details for the file malama-0.1.5-py3-none-any.whl.
File metadata
- Download URL: malama-0.1.5-py3-none-any.whl
- Upload date:
- Size: 13.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2d6cafd412656f626c860d69ea5b15b5be58793b8d087ff47ff64f25731cede4
|
|
| MD5 |
36ff1877932b0f9cca475f175b130088
|
|
| BLAKE2b-256 |
df3408ffa8a82ffae12b819eeb101b104550660be5bd6bb653fa5cd7b39ab67b
|
