chore: Changed name from ragkit to minirag

Author: RaghavOG

.env.example

@@ -16,8 +16,8 @@ OPENAI_API_KEY=sk-...
 # OLLAMA_BASE_URL=http://localhost:11434
 
 # Paths (optional — default: ./data and ./chroma_db in cwd)
-# RAGKIT_DATA_DIR=./data
-# RAGKIT_CHROMA_DIR=./chroma_db
+# MINIRAG_DATA_DIR=./data
+# MINIRAG_CHROMA_DIR=./chroma_db
 
 # Optional overrides
 # EMBEDDING_MODEL=text-embedding-3-small

CHANGELOG.md

@@ -1,20 +1,20 @@
 # Changelog
 
-All notable changes to **RAGKit** (`ragkit` on PyPI) are documented here.
+All notable changes to **MiniRAG** (`minirag` on PyPI) are documented here.
 
 ## [0.1.0] - 2026-07-05
 
 ### Added
-- Production `src/ragkit/` package layout (PyPI-ready)
+- Production `src/minirag/` package layout (PyPI-ready)
 - High-level `RAG` client with multi-provider LLM support (OpenAI, Azure, Anthropic, Gemini, Ollama)
 - Full RAG pipeline: ingest → query rewrite → multi-query retrieval → rerank → generate → guardrails → eval/retry
-- CLI: `ragkit ingest` / `ragkit query`
+- CLI: `minirag ingest` / `minirag query`
 - Optional extras: `[rerank]`, `[anthropic]`, `[gemini]`, `[all]`
 
 ### Changed
-- Renamed public package from `complete-basic-rag` → **`ragkit`**
-- Moved all implementation under installable `src/ragkit/`
-- Data/chroma paths default to cwd (`RAGKIT_DATA_DIR`, `RAGKIT_CHROMA_DIR`)
-- Reranking moved to optional dependency (`pip install ragkit[rerank]`)
+- Renamed public package from `complete-basic-rag` → **`minirag`**
+- Moved all implementation under installable `src/minirag/`
+- Data/chroma paths default to cwd (`MINIRAG_DATA_DIR`, `MINIRAG_CHROMA_DIR`)
+- Reranking moved to optional dependency (`pip install minirag[rerank]`)
 
 [0.1.0]: https://github.com/RaghavOG/rag-python/releases/tag/v0.1.0

README.md

@@ -1,10 +1,10 @@
-# RAGKit
+# MiniRAG
 
 [![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
 [![GitHub](https://img.shields.io/badge/GitHub-RaghavOG%2Frag--python-blue)](https://github.com/RaghavOG/rag-python)
 
-**RAGKit** is a production-oriented Python library for **Retrieval-Augmented Generation (RAG)**.
+**MiniRAG** is a lightweight, production-oriented Python library for **Retrieval-Augmented Generation (RAG)**.
 
 Ingest your documents, ask questions, get grounded answers — with query rewriting, multi-query retrieval, reranking, guardrails, and multi-LLM support.
 
@@ -26,7 +26,7 @@ Ingest your documents, ask questions, get grounded answers — with query rewrit
 ## Install
 
 ```bash
-pip install ragkit
+pip install minirag
 # or from source
 pip install -e .
 # with reranking + extra providers
@@ -38,7 +38,7 @@ pip install -e ".[rerank,anthropic,gemini,all]"
 ## Quickstart
 
 ```python
-from ragkit import RAG
+from minirag import RAG
 
 rag = RAG(
     llm_provider="openai",
@@ -56,8 +56,8 @@ print(answer.text)
 
 ```bash
 export OPENAI_API_KEY=sk-...
-ragkit ingest ./data --reindex
-ragkit query "How many days of annual leave?" -v
+minirag ingest ./data --reindex
+minirag query "How many days of annual leave?" -v
 ```
 
 ---
@@ -73,8 +73,8 @@ ragkit query "How many days of annual leave?" -v
 | `AZURE_OPENAI_API_KEY` | For Azure | Azure OpenAI |
 | `OPENAI_API_VERSION` | Azure | Default `2023-09-01-preview` |
 | `OLLAMA_BASE_URL` | Ollama | Default `http://localhost:11434` |
-| `RAGKIT_DATA_DIR` | Optional | Default `./data` |
-| `RAGKIT_CHROMA_DIR` | Optional | Default `./chroma_db` |
+| `MINIRAG_DATA_DIR` | Optional | Default `./data` |
+| `MINIRAG_CHROMA_DIR` | Optional | Default `./chroma_db` |
 
 See [`.env.example`](.env.example) for all tuning options.
 
@@ -84,7 +84,7 @@ See [`.env.example`](.env.example) for all tuning options.
 
 ```text
 .
-├── src/ragkit/          # Installable package (PyPI)
+├── src/minirag/         # Installable package (PyPI)
 │   ├── client.py        # High-level RAG API
 │   ├── rag_pipeline.py  # Full pipeline
 │   └── providers/       # OpenAI, Azure, Anthropic, Gemini, Ollama

docs/PROVIDERS.md

@@ -1,15 +1,15 @@
 ## Providers
 
-RAGKit separates **LLM provider** (generation, rewriting, guardrails) from **embedding provider** (retrieval).
+MiniRAG separates **LLM provider** (generation, rewriting, guardrails) from **embedding provider** (retrieval).
 
 ### LLM providers
 
 | Provider | `llm_provider=` | Env |
 |----------|-----------------|-----|
 | OpenAI | `openai` | `OPENAI_API_KEY` |
 | Azure OpenAI | `azure_openai` | `AZURE_OPENAI_ENDPOINT`, `AZURE_OPENAI_API_KEY` |
-| Anthropic | `anthropic` | `ANTHROPIC_API_KEY` + `pip install ragkit[anthropic]` |
-| Gemini | `gemini` | `GEMINI_API_KEY` + `pip install ragkit[gemini]` |
+| Anthropic | `anthropic` | `ANTHROPIC_API_KEY` + `pip install minirag[anthropic]` |
+| Gemini | `gemini` | `GEMINI_API_KEY` + `pip install minirag[gemini]` |
 | Ollama | `ollama` | Ollama running locally |
 
 ### Embedding providers
@@ -25,7 +25,7 @@ Anthropic and Gemini are **LLM-only** in this version — pair them with OpenAI
 ### Reranking (optional)
 
 ```bash
-pip install ragkit[rerank]
+pip install minirag[rerank]
 ```
 
 Uses `sentence-transformers` cross-encoder (`BAAI/bge-reranker-base` by default).  

docs/USAGE.md

@@ -3,7 +3,7 @@
 ### Python API
 
 ```python
-from ragkit import RAG
+from minirag import RAG
 
 rag = RAG(
     llm_provider="openai",
@@ -23,8 +23,8 @@ print(ans.evaluation)   # faithfulness / relevance scores
 
 ```bash
 pip install -e .
-ragkit ingest ./data --reindex
-ragkit query "How many days of annual leave?" -v
+minirag ingest ./data --reindex
+minirag query "How many days of annual leave?" -v
 ```
 
 ### Local development

examples/ollama_local.py

@@ -1,20 +1,12 @@
-from ragkit import RAG
-
-
-def main():
-    # Ensure Ollama is running and models are pulled:
-    #   ollama pull llama3.1
-    #   ollama pull mxbai-embed-large
-    rag = RAG(
-        llm_provider="ollama",
-        llm_model="llama3.1",
-        embedding_provider="ollama",
-        embedding_model="mxbai-embed-large",
-    )
-    rag.ingest(["./data"], reindex=True)
-    ans = rag.query("How many days of annual leave?")
-    print(ans.text)
-
-
-if __name__ == "__main__":
-    main()
+from minirag import RAG
+
+rag = RAG(
+    llm_provider="ollama",
+    llm_model="llama3.1",
+    embedding_provider="ollama",
+    embedding_model="mxbai-embed-large",
+)
+
+rag.ingest(["./data"], reindex=True)
+answer = rag.query("How many days of annual leave?")
+print(answer.text)

examples/openai_basic.py

@@ -1,17 +1,12 @@
-from ragkit import RAG
-
-
-def main():
-    rag = RAG(
-        llm_provider="openai",
-        llm_model="gpt-4o-mini",
-        embedding_provider="openai",
-        embedding_model="text-embedding-3-small",
-    )
-    rag.ingest(["./data"], reindex=True)
-    ans = rag.query("How many days of annual leave?")
-    print(ans.text)
-
-
-if __name__ == "__main__":
-    main()
+from minirag import RAG
+
+rag = RAG(
+    llm_provider="openai",
+    llm_model="gpt-4o-mini",
+    embedding_provider="openai",
+    embedding_model="text-embedding-3-small",
+)
+
+rag.ingest(["./data"], reindex=True)
+answer = rag.query("How many days of annual leave?")
+print(answer.text)

main.py

@@ -1,9 +1,9 @@
-"""Thin CLI wrapper for local development (prefer: ragkit CLI after pip install -e .)."""
+"""Thin CLI wrapper for local development (prefer: minirag CLI after pip install -e .)."""
 import argparse
 from pathlib import Path
 
-from ragkit.config import DATA_DIR, CHUNK_STRATEGY
-from ragkit import ingest, query, RAGResponse
+from minirag.config import DATA_DIR, CHUNK_STRATEGY
+from minirag import ingest, query, RAGResponse
 
 
 def cmd_ingest(args):
@@ -34,7 +34,7 @@ def cmd_query(args):
 
 
 def cmd_chat(args):
-    print("RAGKit chat. Type your question. 'quit' or 'exit' to stop.")
+    print("MiniRAG chat. Type your question. 'quit' or 'exit' to stop.")
     while True:
         try:
             q = input("\nYou: ").strip()
@@ -49,7 +49,7 @@ def cmd_chat(args):
 
 
 def main():
-    parser = argparse.ArgumentParser(description="RAGKit (local dev CLI)")
+    parser = argparse.ArgumentParser(description="MiniRAG (local dev CLI)")
     sub = parser.add_subparsers(dest="command", required=True)
 
     ing = sub.add_parser("ingest", help="Load documents, clean, chunk, embed, store")

pyproject.toml

@@ -3,16 +3,16 @@ requires = ["setuptools>=61.0", "wheel"]
 build-backend = "setuptools.build_meta"
 
 [project]
-name = "ragkit"
+name = "minirag"
 version = "0.1.0"
-description = "Production-grade modular RAG: multi-LLM, query rewriting, reranking, guardrails, and evaluation."
+description = "Lightweight production-grade RAG for Python: multi-LLM, query rewriting, reranking, guardrails, and evaluation."
 readme = "README.md"
 license = { text = "MIT" }
 requires-python = ">=3.10"
 authors = [
   { name = "Raghav Singla", email = "raghavog@users.noreply.github.com" },
 ]
-keywords = ["rag", "llm", "embeddings", "chromadb", "openai", "retrieval-augmented-generation"]
+keywords = ["rag", "llm", "embeddings", "chromadb", "openai", "minirag", "retrieval-augmented-generation"]
 classifiers = [
   "Development Status :: 4 - Beta",
   "Intended Audience :: Developers",
@@ -41,10 +41,10 @@ rerank = ["sentence-transformers>=2.2.0", "torch>=2.0.0"]
 anthropic = ["anthropic>=0.20.0"]
 gemini = ["google-genai>=0.3.0"]
 dev = ["pytest>=7.0", "ruff>=0.1.0", "build", "twine"]
-all = ["ragkit[rerank,anthropic,gemini]"]
+all = ["minirag[rerank,anthropic,gemini]"]
 
 [project.scripts]
-ragkit = "ragkit.cli:main"
+minirag = "minirag.cli:main"
 
 [project.urls]
 Homepage = "https://github.com/RaghavOG/rag-python"
@@ -56,7 +56,7 @@ Issues = "https://github.com/RaghavOG/rag-python/issues"
 where = ["src"]
 
 [tool.setuptools.package-data]
-ragkit = ["py.typed"]
+minirag = ["py.typed"]
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]

src/ragkit/__init__.py src/minirag/__init__.pysrc/ragkit/__init__.py renamed to src/minirag/__init__.py

@@ -1,8 +1,8 @@
-"""RAGKit — production-grade modular RAG for Python.
+"""MiniRAG — lightweight production-grade RAG for Python.
 
 Quick start::
 
-    from ragkit import RAG
+    from minirag import RAG
 
     rag = RAG(llm_model="gpt-4o-mini")
     rag.ingest(["./docs"], reindex=True)