Last active
November 29, 2025 12:49
-
-
Save davidmezzetti/d2854ed82f2d0665ec7efdd073d575d7 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # RAG Quick Start | |
| # Easy to use way to get started with RAG using YOUR data | |
| # | |
| # For a complete application see this: https://github.com/neuml/rag | |
| # | |
| # TxtAI has 70+ example notebooks covering everything the framework provides | |
| # Examples: https://neuml.github.io/txtai/examples | |
| # | |
| # Install TxtAI | |
| # pip install txtai[pipeline-data] | |
| import os | |
| from txtai import Embeddings, RAG | |
| from txtai.pipeline import Textractor | |
| # Step 1: Collect files from local directory | |
| # | |
| # Defaults to "data". Set to whereever your files are. | |
| path = "data" | |
| files = [os.path.join(path, f) for f in os.listdir(path) if os.path.isfile(os.path.join(path, f))] | |
| # Step 2: Text Extraction / Chunking | |
| # | |
| # Using section based chunking here. More complex options available such as semantic chunking, iterative chunking etc. | |
| # Documentation: https://neuml.github.io/txtai/pipeline/data/textractor | |
| # Supports Chonkie chunking as well: https://docs.chonkie.ai/oss/chunkers/overview | |
| textractor = Textractor(backend="docling", sections=True) | |
| chunks = [] | |
| for f in files: | |
| for chunk in textractor(f): | |
| chunks.append((f, chunk)) | |
| # Step 3: Build an embeddings database | |
| # | |
| # The `path` parameter sets the vector embeddings model. Supports Hugging Face models, llama.cpp, Ollama, vLLM and more. | |
| # Documentation: https://neuml.github.io/txtai/embeddings/ | |
| embeddings = Embeddings(content=True, path="Qwen/Qwen3-Embedding-0.6B", maxlength=2048) | |
| embeddings.index(chunks) | |
| # Step 4: Create RAG pipeline | |
| # | |
| # Combines an embeddings database and an LLM. | |
| # Supports Hugging Face models, llama.cpp, Ollama, vLLM and more | |
| # Documentation: https://neuml.github.io/txtai/pipeline/text/rag | |
| rag = RAG(embeddings, "Qwen/Qwen3-0.6B", template=""" | |
| Answer the following question using the provided context. | |
| Question: | |
| {question} | |
| Context: | |
| {context} | |
| """, system="You are a friendly assistant", output="flatten") | |
| question = "Summarize the main advancements made by BERT" | |
| print(rag(question, maxlength=2048, stripthink=True)) |
Author
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
This is now an example in TxtAI: https://github.com/neuml/txtai/blob/master/examples/rag_quickstart.py