RAG-framework good first issues (Python)

RAGPipeline ergonomics: ingest_many(), query(top_k=...) override, and RAGResponse.query about 7 hours ago

enhancement good first issue

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

OpenAI LLM Generator about 9 hours ago

enhancement good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

Developer tooling: pre-commit hooks and Dependabot about 18 hours ago

enhancement good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

Single-source the version and add a PyPI release workflow about 18 hours ago

enhancement help wanted

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

Add .gitattributes and normalise mixed CRLF/LF line endings about 18 hours ago

enhancement good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

CI hardening: Python 3.13/3.14, format checks, lint tests/, mypy on all versions, coverage floor about 18 hours ago

enhancement good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

Promote __len__ and add clear() to the Retriever ABC about 18 hours ago

enhancement good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

Ship a py.typed marker so downstream users get type hints (PEP 561) about 18 hours ago

enhancement good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

Command-line interface: ragframework ingest / ragframework query about 18 hours ago

enhancement help wanted

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

TokenChunker: split by model tokens instead of characters about 18 hours ago

enhancement good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

Add structured logging across pipeline stages about 18 hours ago

enhancement good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

Batch embedding calls in RAGPipeline.ingest() about 18 hours ago

enhancement good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

Persist and reload FAISSRetriever and InMemoryRetriever indexes about 18 hours ago

enhancement good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

Metadata filtering in Retriever.retrieve() about 18 hours ago

enhancement help wanted

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

BM25Retriever (lexical) and HybridRetriever — requires passing query text to retrievers about 18 hours ago

enhancement help wanted

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

Add an optional Reranker stage to the pipeline (ABC + cross-encoder implementation) about 18 hours ago

enhancement help wanted

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

DirectoryLoader: ingest a whole folder with per-extension loader dispatch about 18 hours ago

enhancement good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

HTMLLoader for local .html files and web URLs about 18 hours ago

enhancement good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

CSVLoader and JSONLLoader for tabular / record-oriented data about 18 hours ago

enhancement good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

SentenceChunker: enforce a maximum character length per chunk about 18 hours ago

enhancement good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

enhancement help wanted

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

RAGConfig.chunk_size / chunk_overlap / embedding_dim are silently ignored by RAGPipeline about 18 hours ago

bug help wanted

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

docs/getting-started.md renders as plain text (escaped headings, HTML entities, 322 blank lines) about 18 hours ago

bug documentation good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

README roadmap, GOOD_FIRST_ISSUES.md and CHANGELOG are out of date about 18 hours ago

documentation good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

Re-ingesting the same source duplicates chunks in InMemoryRetriever and FAISSRetriever about 18 hours ago

bug help wanted

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

InMemoryRetriever raises raw numpy ValueError on embedding dimension mismatch about 18 hours ago

bug good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

InMemoryRetriever.add() re-normalises the entire matrix on every call (O(N²)) about 18 hours ago

bug good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

FixedSizeChunker accepts chunk_size <= 0 and negative chunk_overlap about 18 hours ago

bug good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

InMemoryRetriever returns every chunk when top_k <= 0 about 18 hours ago

bug good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

TextFileLoader / MarkdownLoader leak UnicodeDecodeError instead of LoaderError about 18 hours ago

bug good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

ChromaDB Retriever Integration 6 days ago

enhancement good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

Async Pipeline Support 6 days ago

enhancement help wanted

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

OpenAI Embeddings Integration 7 days ago

enhancement good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

FAISS Vector Store Retriever 7 days ago

enhancement good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

HuggingFace Sentence Transformers Embedder 8 days ago

enhancement good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

Recursive / Semantic Text Chunker 10 days ago

enhancement good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

DOCX Document Loader 12 days ago

enhancement good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

PDF Document Loader 6 months ago

enhancement good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

Jupyter Notebook Example & Getting-Started Guide 6 months ago

documentation good first issue

adaumsilva/RAG-framework

2

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines. Plug in your own loaders, embedders, vector stores, and generators — or use the built-in implementations to get started in minutes.

Python

adaumsilva/RAG-framework

Open Issues Need Help