ragforge-ml 0.1.0__tar.gz

ragforge_ml-0.1.0/.github/workflows/ci.yml

@@ -0,0 +1,57 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+          cache: pip
+      - run: |
+          python -m pip install --upgrade pip
+          pip install ruff
+      - run: ruff check src tests
+      - run: ruff format --check src tests
+
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10", "3.11", "3.12"]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: pip
+      - name: Install
+        run: |
+          python -m pip install --upgrade pip
+          pip install -e ".[dev,serve,eval]"
+      - name: Run tests
+        run: pytest -m "not slow and not gpu and not network" --cov=ragforge --cov-report=xml
+
+  build:
+    runs-on: ubuntu-latest
+    needs: [lint, test]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+      - run: |
+          python -m pip install --upgrade pip build
+          python -m build
+      - uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/

ragforge_ml-0.1.0/.github/workflows/docs.yml

@@ -0,0 +1,46 @@
+name: docs
+
+on:
+  push:
+    branches: [main]
+    paths:
+      - docs/**
+      - mkdocs.yml
+      - .github/workflows/docs.yml
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+concurrency:
+  group: pages
+  cancel-in-progress: false
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+          cache: pip
+      - run: |
+          python -m pip install --upgrade pip
+          pip install mkdocs-material pymdown-extensions
+      - run: mkdocs build --strict
+      - uses: actions/upload-pages-artifact@v3
+        with:
+          path: site
+
+  deploy:
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    steps:
+      - id: deployment
+        uses: actions/deploy-pages@v4

ragforge_ml-0.1.0/.gitignore

@@ -0,0 +1,57 @@
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+
+.Python
+build/
+dist/
+*.egg-info/
+*.egg
+wheels/
+
+.venv/
+venv/
+env/
+ENV/
+
+.vscode/
+.idea/
+*.swp
+.DS_Store
+
+.pytest_cache/
+.mypy_cache/
+.ruff_cache/
+.coverage
+htmlcov/
+
+.ipynb_checkpoints/
+
+# Indexes and caches
+qdrant_storage/
+.qdrant/
+.cache/
+hf_cache/
+models_cache/
+
+# Eval results
+benchmarks/results/*.json
+benchmarks/results/*.csv
+!benchmarks/results/.gitkeep
+
+# MkDocs build output
+site/
+
+*.log
+logs/
+
+.env
+.env.local
+
+# Large model files
+*.safetensors
+*.bin
+*.gguf
+*.pt
+*.pth

ragforge_ml-0.1.0/.pre-commit-config.yaml

@@ -0,0 +1,16 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.6.9
+    hooks:
+      - id: ruff
+        args: [--fix]
+      - id: ruff-format
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-toml
+      - id: check-added-large-files
+        args: [--maxkb=512]

ragforge_ml-0.1.0/CHANGELOG.md

@@ -0,0 +1,26 @@
+# Changelog
+
+All notable changes to this project are documented here. Format follows
+[Keep a Changelog](https://keepachangelog.com/en/1.1.0/) and adheres to
+[Semantic Versioning](https://semver.org).
+
+## [Unreleased]
+
+## [0.1.0] — 2026-06-18 — first release
+
+### Added
+- `Pipeline` orchestrator wiring encoder → store → reranker → LLM.
+- Ingestion: PDF (pypdf), Markdown (heading-aware), txt/rst loaders.
+- Recursive char chunker with configurable size + overlap.
+- `SentenceTransformerEncoder` defaulting to `BAAI/bge-small-en-v1.5`.
+- Vector stores: `QdrantStore` (embedded + remote), `InMemoryStore`.
+- `BGEReranker` cross-encoder for top-k reranking.
+- LLM backends: `HFLLM` (HuggingFace causal LM) and `QuantizedHFLLM`
+  (via [turboquant-ml](https://github.com/Ademo93/turboquant)).
+- Pure-Python eval metrics: `context_recall`, `answer_relevance`,
+  `faithfulness` + an orchestrator `evaluate()`.
+- FastAPI server: `/health`, `/ingest`, `/ask`.
+- Typer CLI: `rf ingest / ask / eval / serve / info`.
+- pytest suite with a deterministic hash encoder for offline tests.
+- GitHub Actions CI (lint + tests on Python 3.10-3.12 + wheel build).
+- MkDocs Material documentation site.

ragforge_ml-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 RAGforge Contributors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

ragforge_ml-0.1.0/PKG-INFO

@@ -0,0 +1,229 @@
+Metadata-Version: 2.4
+Name: ragforge-ml
+Version: 0.1.0
+Summary: Local-first RAG pipeline — PDF/Markdown ingestion, Qdrant retrieval, bge reranking, and an answer-quality eval harness. Pairs with turboquant-ml for quantized LLM serving.
+Project-URL: Homepage, https://github.com/Ademo93/ragforge
+Project-URL: Repository, https://github.com/Ademo93/ragforge
+Project-URL: Issues, https://github.com/Ademo93/ragforge/issues
+Project-URL: Documentation, https://Ademo93.github.io/ragforge/
+Author: RAGforge Contributors
+License: MIT
+License-File: LICENSE
+Keywords: bge,evaluation,fastapi,llm,qdrant,rag,reranker,retrieval-augmented-generation,sentence-transformers,vector-search
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Text Processing :: Indexing
+Requires-Python: >=3.10
+Requires-Dist: markdown-it-py>=3.0
+Requires-Dist: numpy>=1.24
+Requires-Dist: pydantic>=2.7
+Requires-Dist: pypdf>=4.2
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: qdrant-client>=1.9
+Requires-Dist: rich>=13.7
+Requires-Dist: sentence-transformers>=3.0
+Requires-Dist: torch>=2.2
+Requires-Dist: tqdm>=4.66
+Requires-Dist: transformers>=4.40
+Requires-Dist: typer>=0.12
+Provides-Extra: all
+Requires-Dist: accelerate>=0.30; extra == 'all'
+Requires-Dist: fastapi>=0.111; extra == 'all'
+Requires-Dist: matplotlib>=3.8; extra == 'all'
+Requires-Dist: pandas>=2.2; extra == 'all'
+Requires-Dist: python-multipart>=0.0.9; extra == 'all'
+Requires-Dist: scikit-learn>=1.4; extra == 'all'
+Requires-Dist: turboquant-ml>=0.1; extra == 'all'
+Requires-Dist: uvicorn>=0.30; extra == 'all'
+Provides-Extra: dev
+Requires-Dist: httpx>=0.27; extra == 'dev'
+Requires-Dist: mypy>=1.10; extra == 'dev'
+Requires-Dist: pytest-asyncio>=0.23; extra == 'dev'
+Requires-Dist: pytest-cov>=5.0; extra == 'dev'
+Requires-Dist: pytest>=8.0; extra == 'dev'
+Requires-Dist: ruff>=0.5; extra == 'dev'
+Provides-Extra: eval
+Requires-Dist: pandas>=2.2; extra == 'eval'
+Requires-Dist: scikit-learn>=1.4; extra == 'eval'
+Provides-Extra: quantized
+Requires-Dist: accelerate>=0.30; extra == 'quantized'
+Requires-Dist: turboquant-ml>=0.1; extra == 'quantized'
+Provides-Extra: serve
+Requires-Dist: fastapi>=0.111; extra == 'serve'
+Requires-Dist: python-multipart>=0.0.9; extra == 'serve'
+Requires-Dist: uvicorn>=0.30; extra == 'serve'
+Provides-Extra: viz
+Requires-Dist: matplotlib>=3.8; extra == 'viz'
+Requires-Dist: pandas>=2.2; extra == 'viz'
+Description-Content-Type: text/markdown
+
+<h1 align="center">RAGforge</h1>
+
+<p align="center">
+  <strong>Local-first RAG pipeline — PDF & Markdown ingestion, Qdrant retrieval, bge reranking, and an answer-quality eval harness.</strong>
+  <br>
+  Pairs with <a href="https://github.com/Ademo93/turboquant">turboquant-ml</a> for quantized LLM serving.
+</p>
+
+<p align="center">
+  <a href="https://pypi.org/project/ragforge-ml/"><img alt="PyPI" src="https://img.shields.io/badge/pypi-ragforge--ml-blue"></a>
+  <a href="#"><img alt="Python" src="https://img.shields.io/badge/python-3.10%2B-blue"></a>
+  <a href="#"><img alt="PyTorch" src="https://img.shields.io/badge/pytorch-2.2%2B-ee4c2c"></a>
+  <a href="#"><img alt="License" src="https://img.shields.io/badge/license-MIT-green"></a>
+  <a href="https://Ademo93.github.io/ragforge/"><img alt="Docs" src="https://img.shields.io/badge/docs-mkdocs--material-blue"></a>
+</p>
+
+---
+
+## Why RAGforge?
+
+Most "RAG starter" repos are a 30-line glue between LangChain and OpenAI that nobody can reproduce because it hides retrieval quality, reranking, latency, and cost behind a single `.invoke()` call. **RAGforge is the opposite**: a small, readable, **local-first** pipeline that you can run end-to-end on your own laptop with open-source models, and that ships with an **answer-quality eval harness** so you can actually measure what changing a knob does.
+
+Three opinions:
+
+1. **Local-first.** Default everywhere is open-source: BAAI/bge-small-en-v1.5 for embeddings, BAAI/bge-reranker-base for reranking, Qdrant in **embedded mode** (no Docker required), and any HuggingFace causal LM for generation. No OpenAI key required to try the project.
+2. **Measurable.** Every change should answer the question "did the answer get better?". RAGforge ships `ragforge eval` with built-in `context_recall`, `answer_relevance`, and `faithfulness` metrics — no RAGAS dependency required, but RAGAS-compatible.
+3. **Composable, not framework-y.** Each stage (ingest, embed, retrieve, rerank, generate, evaluate) is one short module behind a small interface. Swap the encoder, swap the vector store, swap the LLM — no `Runnable.invoke()` magic to debug.
+
+## Features
+
+| Stage | Default | Swappable for |
+|---|---|---|
+| **Ingest** | PDF (pypdf), Markdown (markdown-it-py) | Anything that yields `(text, metadata)` |
+| **Chunk** | Recursive char splitter, ~512 tokens, 64 overlap | Token-aware splitter, sentence splitter |
+| **Embed** | `BAAI/bge-small-en-v1.5` (sentence-transformers) | Any sentence-transformers model |
+| **Vector store** | Qdrant (embedded, no server required) | Qdrant remote, in-memory NumPy backend |
+| **Rerank** | `BAAI/bge-reranker-base` | Any cross-encoder |
+| **LLM** | Any HF causal LM | Same model, NF4-quantized via `turboquant-ml` |
+| **Eval** | `context_recall`, `answer_relevance`, `faithfulness` | RAGAS, hand-rolled |
+| **Serve** | FastAPI `/ingest`, `/ask`, `/eval` | — |
+| **CLI** | `ragforge ingest / ask / eval / serve` | — |
+
+## Installation
+
+The PyPI distribution is named **`ragforge-ml`** (the unsuffixed `ragforge`
+name was taken by an unrelated project). Python import and CLI are just
+`ragforge` / `rf`:
+
+```bash
+pip install ragforge-ml                       # core
+pip install "ragforge-ml[serve]"              # + FastAPI
+pip install "ragforge-ml[quantized]"          # + turboquant-ml NF4 path
+pip install "ragforge-ml[all]"                # everything
+```
+
+## 60-second tour
+
+```python
+from ragforge import Pipeline
+
+rag = Pipeline.from_defaults(model_id="Qwen/Qwen2.5-3B-Instruct")
+rag.ingest(["docs/policy.pdf", "notes/onboarding.md"])
+
+answer = rag.ask("What is the maximum reimbursable amount for client lunches?")
+print(answer.text)
+for src in answer.sources:
+    print(f"  {src.score:.3f}  {src.metadata['path']}#chunk{src.metadata['chunk']}")
+```
+
+### CLI
+
+```bash
+rf ingest docs/ --collection company
+rf ask "How do I rotate an API key?" --collection company --k 5
+rf eval datasets/qa.jsonl --collection company --metrics context_recall,faithfulness
+rf serve --collection company --host 0.0.0.0 --port 8080
+```
+
+### Quantized LLM via TurboQuant
+
+```python
+from ragforge import Pipeline
+from ragforge.llm import QuantizedHFLLM
+
+llm = QuantizedHFLLM("meta-llama/Llama-3.2-3B-Instruct", method="bnb-nf4")
+rag = Pipeline.from_defaults(llm=llm)
+```
+
+## Architecture
+
+```
+ragforge/
+├── ingest/        # PDF + Markdown loaders, chunking
+├── embed/         # sentence-transformers wrapper
+├── vectorstore/   # Qdrant embedded + remote
+├── rerank/        # bge-reranker-base
+├── llm/           # HF causal LM + turboquant-ml integration
+├── pipeline.py    # The end-to-end orchestrator
+├── eval/          # context_recall, answer_relevance, faithfulness
+├── serve/         # FastAPI app
+└── cli.py         # ragforge / rf
+```
+
+Each module is short, readable, and replaceable through a small interface
+(`Encoder`, `VectorStore`, `Reranker`, `LLM`). The pipeline calls them in
+order — no DAG, no runnables, no callbacks.
+
+## Eval harness
+
+The reason RAGforge exists. Most RAG projects ship without measuring whether
+their retrieval is any good. RAGforge ships three metrics in pure Python
+(no external API), all RAGAS-compatible:
+
+| Metric | What it measures |
+|---|---|
+| **`context_recall`** | Of the gold-context tokens, what fraction were retrieved? |
+| **`answer_relevance`** | Cosine similarity between the answer and synthetic questions back-generated from the answer (RAGAS recipe) |
+| **`faithfulness`** | Fraction of answer claims that are entailed by the retrieved context (NLI-based, can fall back to embedding overlap) |
+
+```bash
+rf eval datasets/qa.jsonl --collection company
+```
+
+```text
+                            +---------------+--------+
+                            |  metric       |  mean  |
+                            +---------------+--------+
+                            | context_recall|  0.84  |
+                            | answer_rel    |  0.78  |
+                            | faithfulness  |  0.91  |
+                            +---------------+--------+
+                            n=120  ·  latency_p50=620ms  ·  latency_p95=1.4s
+```
+
+## Roadmap
+
+- [x] PDF + Markdown ingestion
+- [x] Recursive char chunker with overlap
+- [x] BGE embeddings + BGE reranker
+- [x] Qdrant embedded + remote
+- [x] FastAPI serve
+- [x] CLI: ingest, ask, eval, serve
+- [x] Eval: context_recall, answer_relevance, faithfulness
+- [x] `turboquant-ml` integration for NF4 LLM serving
+- [ ] Hybrid retrieval (BM25 + dense)
+- [ ] Streaming generation in `/ask`
+- [ ] Notion / Confluence loaders (community PRs welcome)
+- [ ] SQL agent for structured-data questions
+
+## Contributing
+
+See [`docs/CONTRIBUTING.md`](docs/CONTRIBUTING.md).
+
+```bash
+git clone https://github.com/Ademo93/ragforge
+cd ragforge
+pip install -e ".[dev,serve,eval]"
+pytest
+```
+
+## License
+
+[MIT](LICENSE).

ragforge_ml-0.1.0/README.md

@@ -0,0 +1,163 @@
+<h1 align="center">RAGforge</h1>
+
+<p align="center">
+  <strong>Local-first RAG pipeline — PDF & Markdown ingestion, Qdrant retrieval, bge reranking, and an answer-quality eval harness.</strong>
+  <br>
+  Pairs with <a href="https://github.com/Ademo93/turboquant">turboquant-ml</a> for quantized LLM serving.
+</p>
+
+<p align="center">
+  <a href="https://pypi.org/project/ragforge-ml/"><img alt="PyPI" src="https://img.shields.io/badge/pypi-ragforge--ml-blue"></a>
+  <a href="#"><img alt="Python" src="https://img.shields.io/badge/python-3.10%2B-blue"></a>
+  <a href="#"><img alt="PyTorch" src="https://img.shields.io/badge/pytorch-2.2%2B-ee4c2c"></a>
+  <a href="#"><img alt="License" src="https://img.shields.io/badge/license-MIT-green"></a>
+  <a href="https://Ademo93.github.io/ragforge/"><img alt="Docs" src="https://img.shields.io/badge/docs-mkdocs--material-blue"></a>
+</p>
+
+---
+
+## Why RAGforge?
+
+Most "RAG starter" repos are a 30-line glue between LangChain and OpenAI that nobody can reproduce because it hides retrieval quality, reranking, latency, and cost behind a single `.invoke()` call. **RAGforge is the opposite**: a small, readable, **local-first** pipeline that you can run end-to-end on your own laptop with open-source models, and that ships with an **answer-quality eval harness** so you can actually measure what changing a knob does.
+
+Three opinions:
+
+1. **Local-first.** Default everywhere is open-source: BAAI/bge-small-en-v1.5 for embeddings, BAAI/bge-reranker-base for reranking, Qdrant in **embedded mode** (no Docker required), and any HuggingFace causal LM for generation. No OpenAI key required to try the project.
+2. **Measurable.** Every change should answer the question "did the answer get better?". RAGforge ships `ragforge eval` with built-in `context_recall`, `answer_relevance`, and `faithfulness` metrics — no RAGAS dependency required, but RAGAS-compatible.
+3. **Composable, not framework-y.** Each stage (ingest, embed, retrieve, rerank, generate, evaluate) is one short module behind a small interface. Swap the encoder, swap the vector store, swap the LLM — no `Runnable.invoke()` magic to debug.
+
+## Features
+
+| Stage | Default | Swappable for |
+|---|---|---|
+| **Ingest** | PDF (pypdf), Markdown (markdown-it-py) | Anything that yields `(text, metadata)` |
+| **Chunk** | Recursive char splitter, ~512 tokens, 64 overlap | Token-aware splitter, sentence splitter |
+| **Embed** | `BAAI/bge-small-en-v1.5` (sentence-transformers) | Any sentence-transformers model |
+| **Vector store** | Qdrant (embedded, no server required) | Qdrant remote, in-memory NumPy backend |
+| **Rerank** | `BAAI/bge-reranker-base` | Any cross-encoder |
+| **LLM** | Any HF causal LM | Same model, NF4-quantized via `turboquant-ml` |
+| **Eval** | `context_recall`, `answer_relevance`, `faithfulness` | RAGAS, hand-rolled |
+| **Serve** | FastAPI `/ingest`, `/ask`, `/eval` | — |
+| **CLI** | `ragforge ingest / ask / eval / serve` | — |
+
+## Installation
+
+The PyPI distribution is named **`ragforge-ml`** (the unsuffixed `ragforge`
+name was taken by an unrelated project). Python import and CLI are just
+`ragforge` / `rf`:
+
+```bash
+pip install ragforge-ml                       # core
+pip install "ragforge-ml[serve]"              # + FastAPI
+pip install "ragforge-ml[quantized]"          # + turboquant-ml NF4 path
+pip install "ragforge-ml[all]"                # everything
+```
+
+## 60-second tour
+
+```python
+from ragforge import Pipeline
+
+rag = Pipeline.from_defaults(model_id="Qwen/Qwen2.5-3B-Instruct")
+rag.ingest(["docs/policy.pdf", "notes/onboarding.md"])
+
+answer = rag.ask("What is the maximum reimbursable amount for client lunches?")
+print(answer.text)
+for src in answer.sources:
+    print(f"  {src.score:.3f}  {src.metadata['path']}#chunk{src.metadata['chunk']}")
+```
+
+### CLI
+
+```bash
+rf ingest docs/ --collection company
+rf ask "How do I rotate an API key?" --collection company --k 5
+rf eval datasets/qa.jsonl --collection company --metrics context_recall,faithfulness
+rf serve --collection company --host 0.0.0.0 --port 8080
+```
+
+### Quantized LLM via TurboQuant
+
+```python
+from ragforge import Pipeline
+from ragforge.llm import QuantizedHFLLM
+
+llm = QuantizedHFLLM("meta-llama/Llama-3.2-3B-Instruct", method="bnb-nf4")
+rag = Pipeline.from_defaults(llm=llm)
+```
+
+## Architecture
+
+```
+ragforge/
+├── ingest/        # PDF + Markdown loaders, chunking
+├── embed/         # sentence-transformers wrapper
+├── vectorstore/   # Qdrant embedded + remote
+├── rerank/        # bge-reranker-base
+├── llm/           # HF causal LM + turboquant-ml integration
+├── pipeline.py    # The end-to-end orchestrator
+├── eval/          # context_recall, answer_relevance, faithfulness
+├── serve/         # FastAPI app
+└── cli.py         # ragforge / rf
+```
+
+Each module is short, readable, and replaceable through a small interface
+(`Encoder`, `VectorStore`, `Reranker`, `LLM`). The pipeline calls them in
+order — no DAG, no runnables, no callbacks.
+
+## Eval harness
+
+The reason RAGforge exists. Most RAG projects ship without measuring whether
+their retrieval is any good. RAGforge ships three metrics in pure Python
+(no external API), all RAGAS-compatible:
+
+| Metric | What it measures |
+|---|---|
+| **`context_recall`** | Of the gold-context tokens, what fraction were retrieved? |
+| **`answer_relevance`** | Cosine similarity between the answer and synthetic questions back-generated from the answer (RAGAS recipe) |
+| **`faithfulness`** | Fraction of answer claims that are entailed by the retrieved context (NLI-based, can fall back to embedding overlap) |
+
+```bash
+rf eval datasets/qa.jsonl --collection company
+```
+
+```text
+                            +---------------+--------+
+                            |  metric       |  mean  |
+                            +---------------+--------+
+                            | context_recall|  0.84  |
+                            | answer_rel    |  0.78  |
+                            | faithfulness  |  0.91  |
+                            +---------------+--------+
+                            n=120  ·  latency_p50=620ms  ·  latency_p95=1.4s
+```
+
+## Roadmap
+
+- [x] PDF + Markdown ingestion
+- [x] Recursive char chunker with overlap
+- [x] BGE embeddings + BGE reranker
+- [x] Qdrant embedded + remote
+- [x] FastAPI serve
+- [x] CLI: ingest, ask, eval, serve
+- [x] Eval: context_recall, answer_relevance, faithfulness
+- [x] `turboquant-ml` integration for NF4 LLM serving
+- [ ] Hybrid retrieval (BM25 + dense)
+- [ ] Streaming generation in `/ask`
+- [ ] Notion / Confluence loaders (community PRs welcome)
+- [ ] SQL agent for structured-data questions
+
+## Contributing
+
+See [`docs/CONTRIBUTING.md`](docs/CONTRIBUTING.md).
+
+```bash
+git clone https://github.com/Ademo93/ragforge
+cd ragforge
+pip install -e ".[dev,serve,eval]"
+pytest
+```
+
+## License
+
+[MIT](LICENSE).

ragforge_ml-0.1.0/data/sample/company-policy.md

@@ -0,0 +1,28 @@
+# Refund policy
+
+Refunds are processed within 14 days of the original purchase date for any
+reason, no questions asked. Refunds are issued to the original payment method.
+
+# Returns
+
+Returns are accepted within 30 days of delivery. Items must be returned in
+their original packaging with proof of purchase. Shipping costs for returns
+are borne by the customer unless the item is defective.
+
+# Shipping
+
+Standard shipping takes 3-5 business days. Express shipping is available for
+an additional 12 EUR and ships within 1 business day. Orders above 50 EUR
+qualify for free standard shipping.
+
+# Account & API keys
+
+To rotate an API key, log in to your account, navigate to Settings > API
+Keys, and click "Rotate". The old key remains valid for 24 hours to ease
+transitions. API keys must be kept secret and never committed to source
+control.
+
+# Support
+
+Reach support at support@example.com. Median response time is 4 hours during
+business days (Monday-Friday, 9am-6pm CET).

ragforge_ml-0.1.0/data/sample/qa.jsonl

@@ -0,0 +1,5 @@
+{"question": "How long is the refund window?", "ground_truth": "14 days"}
+{"question": "Within how many days can I return an item?", "ground_truth": "30 days"}
+{"question": "When do I get free shipping?", "ground_truth": "above 50 EUR"}
+{"question": "How do I rotate an API key?", "ground_truth": "go to Settings > API Keys and click Rotate"}
+{"question": "What is the support response time?", "ground_truth": "4 hours median during business days"}