raghilda 0.1.0__tar.gz

raghilda-0.1.0/PKG-INFO

@@ -0,0 +1,95 @@
+Metadata-Version: 2.4
+Name: raghilda
+Version: 0.1.0
+Summary: RAG made simple
+Author: Daniel Falbel, Tomasz Kalinowski
+Author-email: Daniel Falbel <daniel@posit.co>, Tomasz Kalinowski <tomasz@posit.co>
+License-Expression: MIT
+Requires-Dist: duckdb>=1.3.2
+Requires-Dist: openai>=1.104.2
+Requires-Dist: requests>=2.32.5
+Requires-Dist: commonmark>=0.9.1
+Requires-Dist: markitdown>=0.1.3
+Requires-Dist: tqdm>=4.67.1
+Requires-Dist: chromadb>=1.0.0 ; extra == 'chromadb'
+Requires-Dist: chatlas>=0.2.0 ; extra == 'examples'
+Requires-Dist: python-dotenv>=1.0.0 ; extra == 'examples'
+Requires-Dist: sentence-transformers>=3.0.0 ; extra == 'sentence-transformers'
+Requires-Dist: pyright>=1.1.405 ; extra == 'test'
+Requires-Dist: pytest>=8.4.1 ; extra == 'test'
+Requires-Dist: ruff>=0.12.11 ; extra == 'test'
+Requires-Dist: chonkie>=1.0.0 ; extra == 'test'
+Requires-Dist: cohere>=5.0.0 ; extra == 'test'
+Requires-Dist: chromadb>=1.0.0 ; extra == 'test'
+Requires-Dist: sentence-transformers>=3.0.0 ; extra == 'test'
+Requires-Python: >=3.11, <3.14
+Project-URL: Repository, https://github.com/dfalbel/raghilda
+Provides-Extra: chromadb
+Provides-Extra: examples
+Provides-Extra: sentence-transformers
+Provides-Extra: test
+Description-Content-Type: text/markdown
+
+# raghilda <img src="assets/raghilda-logo.png" align="right" width="140" alt="raghilda hex logo" />
+
+RAG made simple.
+
+raghilda is a Python package for implementing Retrieval-Augmented Generation (RAG) workflows. It provides a complete solution with sensible defaults while remaining transparent—not a black box.
+
+## Installation
+
+```bash
+pip install raghilda
+```
+
+Or install from GitHub:
+
+```bash
+pip install git+https://github.com/dfalbel/raghilda.git
+```
+
+## Key Steps
+
+raghilda handles the complete RAG pipeline:
+
+1. **Document Processing** — Convert documents to Markdown using MarkItDown
+2. **Text Chunking** — Split text at semantic boundaries (headings, paragraphs, sentences)
+3. **Embedding** — Generate vector representations via OpenAI or other providers
+4. **Storage** — Store chunks and embeddings in DuckDB, ChromaDB, or OpenAI Vector Stores
+5. **Retrieval** — Find relevant chunks using similarity search or BM25
+
+## Usage
+
+```python
+from raghilda.store import DuckDBStore
+from raghilda.embedding import EmbeddingOpenAI
+from raghilda.scrape import find_links
+from raghilda.read import read_as_markdown
+from raghilda.chunker import MarkdownChunker
+
+# Create a store with embeddings
+store = DuckDBStore.create(
+    location="chatlas.db",
+    embed=EmbeddingOpenAI(),
+)
+
+# Find and index pages from the chatlas documentation
+links = find_links("https://posit-dev.github.io/chatlas/")
+chunker = MarkdownChunker()
+
+for link in links:
+    document = read_as_markdown(link)
+    chunked_document = chunker.chunk(document)
+    store.upsert(chunked_document)
+
+# Retrieve relevant chunks
+chunks = store.retrieve("How do I stream a response?", top_k=5)
+for chunk in chunks:
+    print(chunk.text)
+```
+
+## Links
+
+- [Documentation](https://dfalbel.github.io/raghilda/)
+- [Source Code](https://github.com/dfalbel/raghilda)
+- [Report Issues](https://github.com/dfalbel/raghilda/issues)

raghilda-0.1.0/README.md

@@ -0,0 +1,63 @@
+# raghilda <img src="assets/raghilda-logo.png" align="right" width="140" alt="raghilda hex logo" />
+
+RAG made simple.
+
+raghilda is a Python package for implementing Retrieval-Augmented Generation (RAG) workflows. It provides a complete solution with sensible defaults while remaining transparent—not a black box.
+
+## Installation
+
+```bash
+pip install raghilda
+```
+
+Or install from GitHub:
+
+```bash
+pip install git+https://github.com/dfalbel/raghilda.git
+```
+
+## Key Steps
+
+raghilda handles the complete RAG pipeline:
+
+1. **Document Processing** — Convert documents to Markdown using MarkItDown
+2. **Text Chunking** — Split text at semantic boundaries (headings, paragraphs, sentences)
+3. **Embedding** — Generate vector representations via OpenAI or other providers
+4. **Storage** — Store chunks and embeddings in DuckDB, ChromaDB, or OpenAI Vector Stores
+5. **Retrieval** — Find relevant chunks using similarity search or BM25
+
+## Usage
+
+```python
+from raghilda.store import DuckDBStore
+from raghilda.embedding import EmbeddingOpenAI
+from raghilda.scrape import find_links
+from raghilda.read import read_as_markdown
+from raghilda.chunker import MarkdownChunker
+
+# Create a store with embeddings
+store = DuckDBStore.create(
+    location="chatlas.db",
+    embed=EmbeddingOpenAI(),
+)
+
+# Find and index pages from the chatlas documentation
+links = find_links("https://posit-dev.github.io/chatlas/")
+chunker = MarkdownChunker()
+
+for link in links:
+    document = read_as_markdown(link)
+    chunked_document = chunker.chunk(document)
+    store.upsert(chunked_document)
+
+# Retrieve relevant chunks
+chunks = store.retrieve("How do I stream a response?", top_k=5)
+for chunk in chunks:
+    print(chunk.text)
+```
+
+## Links
+
+- [Documentation](https://dfalbel.github.io/raghilda/)
+- [Source Code](https://github.com/dfalbel/raghilda)
+- [Report Issues](https://github.com/dfalbel/raghilda/issues)

raghilda-0.1.0/pyproject.toml

@@ -0,0 +1,58 @@
+[project]
+name = "raghilda"
+version = "0.1.0"
+description = "RAG made simple"
+license = "MIT"
+readme = "README.md"
+authors = [
+    { name = "Daniel Falbel", email = "daniel@posit.co" },
+    { name = "Tomasz Kalinowski", email = "tomasz@posit.co" },
+]
+requires-python = ">=3.11, <3.14"
+dependencies = [
+    "duckdb>=1.3.2",
+    "openai>=1.104.2",
+    "requests>=2.32.5",
+    "commonmark>=0.9.1",
+    "markitdown>=0.1.3",
+    "tqdm>=4.67.1",
+]
+
+[project.urls]
+Repository = "https://github.com/dfalbel/raghilda"
+
+[build-system]
+requires = ["uv_build>=0.8.0,<0.9"]
+build-backend = "uv_build"
+
+[project.optional-dependencies]
+test = ["pyright>=1.1.405", "pytest>=8.4.1", "ruff>=0.12.11", "chonkie>=1.0.0", "cohere>=5.0.0", "chromadb>=1.0.0", "sentence-transformers>=3.0.0"]
+examples = ["chatlas>=0.2.0", "python-dotenv>=1.0.0"]
+chromadb = ["chromadb>=1.0.0"]
+sentence-transformers = ["sentence-transformers>=3.0.0"]
+
+[dependency-groups]
+dev = [
+    "dotenv>=0.9.9",
+    "great-docs",
+    "griffe>=1.5.0,<2.0",
+    "taskipy>=1.14.1",
+]
+
+[tool.taskipy.tasks]
+docs_build = { cmd = "./.venv/bin/great-docs build", help = "build docs" }
+docs_preview = { cmd = "./.venv/bin/great-docs preview", help = "build docs and launch preview" }
+docs = { cmd = "./.venv/bin/great-docs preview", help = "build docs and launch preview" }
+tests = { cmd = "./.venv/bin/pytest tests src", help = "run pytest suite" }
+types_check = { cmd = "./.venv/bin/pyright --pythonpath ./.venv/bin/python", help = "run pyright" }
+format = { cmd = "./.venv/bin/ruff format src tests", help = "format code" }
+format_check = { cmd = "./.venv/bin/ruff format --check src tests", help = "format check" }
+lint_check = { cmd = "./.venv/bin/ruff check", help = "ruff lint" }
+lint = { cmd = "./.venv/bin/ruff check --fix", help = "ruff lint --fix" }
+check = { cmd = "./.venv/bin/ruff format --check src tests && ./.venv/bin/ruff check && ./.venv/bin/pyright --pythonpath ./.venv/bin/python && ./.venv/bin/pytest tests src", help = "format+lint+types+tests" }
+
+[tool.pyright]
+exclude = [".venv", ".pytest_cache", ".ruff_cache", "great-docs"]
+
+[tool.uv.sources]
+great-docs = { git = "https://github.com/rich-iannone/great-docs.git" }

raghilda-0.1.0/src/raghilda/__init__.py

@@ -0,0 +1,12 @@
+from . import embedding, store, types, chunk, chunker, document, read, scrape
+
+__all__ = [
+    "embedding",
+    "store",
+    "types",
+    "chunk",
+    "chunker",
+    "document",
+    "read",
+    "scrape",
+]