longparser 0.1.0__py3-none-any.whl

longparser-0.1.0.dist-info/METADATA

@@ -0,0 +1,337 @@
+Metadata-Version: 2.4
+Name: longparser
+Version: 0.1.0
+Summary: Privacy-first document intelligence engine — converts PDFs, DOCX, PPTX, XLSX, and CSV into AI-ready Markdown + structured JSON for RAG pipelines.
+Author-email: ENDEVSOLS Team <dev@endevsols.com>
+License: MIT
+Project-URL: Homepage, https://github.com/ENDEVSOLS/LongParser
+Project-URL: Repository, https://github.com/ENDEVSOLS/LongParser
+Project-URL: Issues, https://github.com/ENDEVSOLS/LongParser/issues
+Project-URL: Documentation, https://endevsols.github.io/LongParser/
+Project-URL: Changelog, https://github.com/ENDEVSOLS/LongParser/blob/main/CHANGELOG.md
+Keywords: pdf,document,parsing,ocr,rag,ai,docling,chunking,extraction,retrieval-augmented-generation,longparser
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Text Processing :: General
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: pydantic<3,>=2.0
+Requires-Dist: docling>=2.14
+Requires-Dist: docling-core>=2.13
+Provides-Extra: pptx
+Requires-Dist: python-pptx>=1.0; extra == "pptx"
+Provides-Extra: langchain
+Requires-Dist: langchain-core>=0.2; extra == "langchain"
+Provides-Extra: llamaindex
+Requires-Dist: llama-index-core>=0.10; extra == "llamaindex"
+Provides-Extra: server
+Requires-Dist: fastapi>=0.115; extra == "server"
+Requires-Dist: uvicorn[standard]>=0.34; extra == "server"
+Requires-Dist: python-multipart>=0.0.9; extra == "server"
+Requires-Dist: motor>=3.6; extra == "server"
+Requires-Dist: arq>=0.26; extra == "server"
+Requires-Dist: python-magic>=0.4.27; extra == "server"
+Requires-Dist: python-dotenv>=1.0; extra == "server"
+Requires-Dist: langchain>=0.3; extra == "server"
+Requires-Dist: langchain-openai>=0.3; extra == "server"
+Requires-Dist: langchain-google-genai>=2.0; extra == "server"
+Requires-Dist: langchain-groq>=0.3; extra == "server"
+Requires-Dist: langchain-mongodb>=0.3; extra == "server"
+Requires-Dist: langchain-huggingface>=0.1; extra == "server"
+Requires-Dist: langchain-chroma>=0.2; extra == "server"
+Requires-Dist: langgraph>=0.2; extra == "server"
+Requires-Dist: langgraph-checkpoint>=2.0; extra == "server"
+Requires-Dist: tiktoken>=0.7; extra == "server"
+Requires-Dist: redis>=5.0; extra == "server"
+Provides-Extra: embeddings
+Requires-Dist: sentence-transformers>=3.0; extra == "embeddings"
+Provides-Extra: chroma
+Requires-Dist: chromadb>=0.5; extra == "chroma"
+Provides-Extra: faiss
+Requires-Dist: faiss-cpu>=1.8; extra == "faiss"
+Provides-Extra: qdrant
+Requires-Dist: qdrant-client>=1.12; extra == "qdrant"
+Provides-Extra: latex-ocr
+Requires-Dist: pix2tex>=0.1.4; extra == "latex-ocr"
+Provides-Extra: docx-equations
+Requires-Dist: docxlatex>=0.3.0; extra == "docx-equations"
+Requires-Dist: defusedxml>=0.7.0; extra == "docx-equations"
+Provides-Extra: mfd
+Requires-Dist: pix2text<1.2,>=1.1.1; extra == "mfd"
+Provides-Extra: all
+Requires-Dist: longparser[pptx]; extra == "all"
+Requires-Dist: longparser[langchain]; extra == "all"
+Requires-Dist: longparser[llamaindex]; extra == "all"
+Requires-Dist: longparser[server]; extra == "all"
+Requires-Dist: longparser[embeddings]; extra == "all"
+Requires-Dist: longparser[chroma]; extra == "all"
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.23; extra == "dev"
+Requires-Dist: pytest-cov>=5.0; extra == "dev"
+Requires-Dist: ruff>=0.4; extra == "dev"
+Requires-Dist: mypy>=1.10; extra == "dev"
+Requires-Dist: build>=1.0; extra == "dev"
+Requires-Dist: twine>=5.0; extra == "dev"
+Requires-Dist: httpx>=0.27; extra == "dev"
+Requires-Dist: anyio>=4.0; extra == "dev"
+
+<p align="center">
+  <!-- Logo goes here once ready -->
+  <h1 align="center">LongParser</h1>
+  <p align="center"><strong>Privacy-first document intelligence engine for production RAG pipelines.</strong></p>
+  <p align="center">
+    Parse PDFs, DOCX, PPTX, XLSX &amp; CSV → validated, AI-ready chunks with HITL review.
+  </p>
+  <p align="center">
+    <a href="https://github.com/ENDEVSOLS/LongParser/actions/workflows/ci.yml">
+      <img src="https://github.com/ENDEVSOLS/LongParser/actions/workflows/ci.yml/badge.svg" alt="CI">
+    </a>
+    <a href="https://pypi.org/project/longparser/">
+      <img src="https://img.shields.io/pypi/v/longparser.svg?label=pypi&color=0078d4" alt="PyPI">
+    </a>
+    <a href="https://pypi.org/project/longparser/">
+      <img src="https://img.shields.io/pypi/dm/longparser.svg?label=downloads&color=28a745" alt="Downloads">
+    </a>
+    <a href="https://www.python.org/">
+      <img src="https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12-blue.svg" alt="Python">
+    </a>
+    <a href="LICENSE">
+      <img src="https://img.shields.io/badge/License-MIT-brightgreen.svg" alt="MIT License">
+    </a>
+    <a href="https://endevsols.github.io/LongParser/">
+      <img src="https://img.shields.io/badge/docs-online-indigo.svg" alt="Docs">
+    </a>
+  </p>
+</p>
+
+---
+
+
+## Features
+
+| Feature | Detail |
+|---------|--------|
+| **Multi-format extraction** | PDF, DOCX, PPTX, XLSX, CSV via Docling |
+| **Hybrid chunking** | Token-aware, heading-hierarchy-aware, table-aware |
+| **HITL review** | Human-in-the-Loop block & chunk editing before embedding |
+| **LangGraph HITL** | `approve / edit / reject` workflow with LangGraph `interrupt()` |
+| **3-layer memory** | Short-term turns + rolling summary + long-term facts |
+| **Multi-provider LLM** | OpenAI, Gemini, Groq, OpenRouter |
+| **Multi-backend vectors** | Chroma, FAISS, Qdrant |
+| **Async-first API** | FastAPI + Motor (MongoDB) + ARQ (Redis) |
+| **LangChain adapters** | Drop-in `BaseRetriever` and LlamaIndex `QueryEngine` |
+| **Privacy-first** | All processing runs locally; no data leaves your infra |
+
+---
+
+## Installation
+
+### Core (SDK only — no API server)
+
+```bash
+pip install longparser
+```
+
+### With REST API server (FastAPI + MongoDB + LLM)
+
+```bash
+pip install "longparser[server]"
+```
+
+### All extras
+
+```bash
+pip install "longparser[all]"
+```
+
+---
+
+## Quick Start
+
+### Python SDK
+
+```python
+from longparser import PipelineOrchestrator, ProcessingConfig
+
+pipeline = PipelineOrchestrator()
+result = pipeline.process_file("document.pdf")
+
+print(f"Pages: {result.document.metadata.total_pages}")
+print(f"Chunks: {len(result.chunks)}")
+print(result.chunks[0].text)
+```
+
+### REST API
+
+```bash
+# 1. Copy and edit configuration
+cp .env.example .env
+
+# 2. Start services (MongoDB + Redis)
+docker-compose up -d mongo redis
+
+# 3. Start the API
+uv run uvicorn longparser.server.app:app --reload --port 8000
+
+# 4. Upload a document
+curl -X POST http://localhost:8000/jobs \
+  -H "X-API-Key: your-key" \
+  -F "file=@document.pdf"
+
+# 5. Check job status
+curl http://localhost:8000/jobs/{job_id} -H "X-API-Key: your-key"
+
+# 6. Finalize and embed
+curl -X POST http://localhost:8000/jobs/{job_id}/finalize \
+  -H "X-API-Key: your-key" \
+  -H "Content-Type: application/json" \
+  -d '{"finalize_policy": "approve_all_pending"}'
+
+curl -X POST http://localhost:8000/jobs/{job_id}/embed \
+  -H "X-API-Key: your-key" \
+  -H "Content-Type: application/json" \
+  -d '{"provider": "huggingface", "model": "BAAI/bge-base-en-v1.5", "vector_db": "chroma"}'
+
+# 7. Chat with the document
+curl -X POST http://localhost:8000/chat/sessions \
+  -H "X-API-Key: your-key" \
+  -H "Content-Type: application/json" \
+  -d '{"job_id": "your-job-id"}'
+
+curl -X POST http://localhost:8000/chat \
+  -H "X-API-Key: your-key" \
+  -H "Content-Type: application/json" \
+  -d '{"session_id": "...", "job_id": "...", "question": "What is the refund policy?"}'
+```
+
+---
+
+## Architecture
+
+```
+Document → Extract → Validate → HITL Review → Chunk → Embed → Index
+                                                              ↓
+                                             Chat → RAG → LLM → Answer
+```
+
+### Pipeline Stages
+
+1. **Extract** — Docling converts PDF/DOCX/etc. into structured `Block` objects
+2. **Validate** — Per-page confidence scoring and RTL detection
+3. **HITL Review** — Human approves/edits/rejects blocks and chunks via the API
+4. **Chunk** — `HybridChunker` builds token-aware RAG chunks with section hierarchy
+5. **Embed** — Embedding engine (HuggingFace / OpenAI) vectors stored in Chroma/FAISS/Qdrant
+6. **Chat** — LCEL chain with 3-layer memory and citation validation
+
+---
+
+## Project Structure
+
+```
+src/longparser/
+├── schemas.py           ← core Pydantic models (Document, Block, Chunk, …)
+├── extractors/          ← Docling, LaTeX OCR backends
+├── chunkers/            ← HybridChunker
+├── pipeline/            ← PipelineOrchestrator
+├── integrations/        ← LangChain loader & LlamaIndex reader
+├── utils/               ← shared helpers (RTL detection, …)
+└── server/              ← REST API layer
+    ├── app.py           ← FastAPI application (all routes)
+    ├── db.py            ← Motor async MongoDB
+    ├── queue.py         ← ARQ/Redis job queue
+    ├── worker.py        ← ARQ background worker
+    ├── embeddings.py    ← HuggingFace / OpenAI embedding engine
+    ├── vectorstores.py  ← Chroma / FAISS / Qdrant adapters
+    └── chat/            ← RAG chat engine
+        ├── engine.py    ← ChatEngine (LCEL + 3-layer memory)
+        ├── graph.py     ← LangGraph HITL workflow
+        ├── schemas.py   ← chat Pydantic models
+        ├── retriever.py ← LangChain BaseRetriever adapter
+        ├── llm_chain.py ← multi-provider LLM factory
+        └── callbacks.py ← observability callbacks
+```
+
+---
+
+## LangChain Integration
+
+```python
+from longparser.integrations.langchain import LongParserLoader
+
+loader = LongParserLoader("report.pdf")
+docs = loader.load()  # list[langchain_core.documents.Document]
+```
+
+## LlamaIndex Integration
+
+```python
+from longparser.integrations.llamaindex import LongParserReader
+
+reader = LongParserReader()
+docs = reader.load_data("report.pdf")
+```
+
+---
+
+## Configuration
+
+Copy `.env.example` to `.env` and set:
+
+| Variable | Default | Description |
+|----------|---------|-------------|
+| `LONGPARSER_MONGO_URL` | `mongodb://localhost:27017` | MongoDB connection |
+| `LONGPARSER_REDIS_URL` | `redis://localhost:6379` | Redis for job queue |
+| `LONGPARSER_LLM_PROVIDER` | `openai` | LLM provider |
+| `LONGPARSER_LLM_MODEL` | `gpt-4o` | Model name |
+| `LONGPARSER_EMBED_PROVIDER` | `huggingface` | Embedding provider |
+| `LONGPARSER_VECTOR_DB` | `chroma` | Vector store backend |
+
+---
+
+## Running with Docker
+
+```bash
+docker-compose up
+```
+
+API available at `http://localhost:8000` · Docs at `http://localhost:8000/docs`
+
+---
+
+## Testing
+
+```bash
+# Install dev dependencies
+uv sync --extra dev
+
+# Run unit tests
+uv run pytest tests/unit/ -v
+
+# Run with coverage
+uv run pytest tests/ --cov=src/longparser --cov-report=term-missing
+```
+
+---
+
+## Contributing
+
+See [CONTRIBUTING.md](CONTRIBUTING.md) for development setup and PR guidelines.
+
+## Security
+
+See [SECURITY.md](SECURITY.md) for vulnerability reporting.
+
+## License
+
+[MIT](LICENSE) — Copyright © 2026 ENDEVSOLS

longparser-0.1.0.dist-info/RECORD

@@ -0,0 +1,36 @@
+longparser/__init__.py,sha256=TxZ2xrbXkOS_GRMxW1ALyUx2VLPLqT13EZutkf1BHPw,2652
+longparser/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+longparser/schemas.py,sha256=u2iLPzwkLJhTQIxv35x6YHa84eGcqn-dmxLpPl9cqQA,8358
+longparser/chunkers/__init__.py,sha256=a_GG6Jq7rivT-6smjKaepJ05a6Yw3lox2jVud8ZXN6I,147
+longparser/chunkers/hybrid_chunker.py,sha256=3O-ULwDSrfUTK3SYbho_VCG4fJ_Xy7bzuV_HG1JsdlI,38493
+longparser/extractors/__init__.py,sha256=DAvcSWFsktKyBevda-MQz7FNvOwCFoFZR0mBZfiU0M4,183
+longparser/extractors/base.py,sha256=GewwQQhnFrro2YUzUQUnroAlzWZoPDWmaE8R6gx4RUw,1589
+longparser/extractors/docling_extractor.py,sha256=dbZX1wdlquxec4DtKpV9vsvKbcOr1_5TU-KBlmitxRQ,87767
+longparser/extractors/latex_ocr.py,sha256=g4UvWYXZgVtq-runyT9IR-y_QCPZfVuT6ujLsDNcLSA,13576
+longparser/integrations/__init__.py,sha256=eUOKAefM601hp99-Cb0cZpvjeH4uBGftWAd2fCOX2e4,705
+longparser/integrations/langchain.py,sha256=tplNfuN5VXrZtLJle-dnEk_AYJ15dkS9apSHLaMtvUg,4719
+longparser/integrations/llamaindex.py,sha256=KzcY8Hl_sge1e10O7zKU9tRayjaqgAZ8y2U7tI3cBFs,5114
+longparser/pipeline/__init__.py,sha256=-35EKBAADEMOKb8jsWb6sy21HDk5XI0pMH-iQ5M8gc4,187
+longparser/pipeline/orchestrator.py,sha256=X2I59RoqxWyYwikboS_wNZkkbE80yIoERCeiwcb2lg4,8043
+longparser/server/__init__.py,sha256=9nwpSCCYvFxGpMjf8wKxuVULkNqSB4At8mozOMwyTJ8,836
+longparser/server/app.py,sha256=3_gyQqBXbkjNloH-QdGUir_fcDWnND2-jVzcsOVG2Wg,35558
+longparser/server/db.py,sha256=O47Khi3o-bz12fnUDH2lkiGotCI7hF8pHFqDHUh64ds,24267
+longparser/server/embeddings.py,sha256=Fex2CLi0snho0o8eISgSTvVRmXtF2jk_yJDL1tNtado,6909
+longparser/server/queue.py,sha256=pBew2qUPgr9Uhia7Dip71N9w-LEsZWVQW0IlA-67StA,3153
+longparser/server/schemas.py,sha256=ikquG9V0ZlYdl_YumN374LMsx00jTq5F52kJDRtWLX8,5886
+longparser/server/vectorstores.py,sha256=CjwV6cBlbrA7nwqtGp3THsyCmlO6mGRhe-qgIhKZPwM,15868
+longparser/server/worker.py,sha256=vSLLTr70ScL3SOEPcPCyFtlfouEop14Q6J5wYHvdNjA,17133
+longparser/server/chat/__init__.py,sha256=Oc-NHMqhPjQzx6H0EsOkfUaMBW7fInHvyBnixphVgHY,1171
+longparser/server/chat/callbacks.py,sha256=-k3ewXUTuiFlrwDw3uy_jBzwcqWBeDf6ylHdWb8a4Qs,3189
+longparser/server/chat/engine.py,sha256=o4lHMPNdiMsjrILUaxEiicfgONeF2leWT04-rQWndZs,12523
+longparser/server/chat/graph.py,sha256=sFjZw5KuD24u1PxOGTyL8if2Om7z0ul_HoZwMfQ4kQk,5298
+longparser/server/chat/llm_chain.py,sha256=5sfDD8w2mnD1BC1Zoz2SDbG7Qe3WkjurCG8MypjPBx0,4542
+longparser/server/chat/retriever.py,sha256=D00ciMzgqQwvXWGCce-ucoAMRXh14FWNfWtIPMg5ANI,3855
+longparser/server/chat/schemas.py,sha256=1joowXGwMjlb_KlQ7LukNu45QS7E1GazT9QIQN6LOMs,5646
+longparser/server/routers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+longparser/utils/__init__.py,sha256=au_LfIWxlufiGOs_hhNHvLKdHlAlKBPCFl7VTQ7yEWQ,120
+longparser/utils/rtl_detector.py,sha256=aSN6G1YR_jBkkbZzV-UDQEZIyR-DyIJ9s8pPftCoLAk,2632
+longparser-0.1.0.dist-info/METADATA,sha256=yc57l2SxFXlBePNanqkH7GoqdlOTUZqzPTAVAs11pCA,11601
+longparser-0.1.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+longparser-0.1.0.dist-info/top_level.txt,sha256=KcsuWnbKnEnDl2f31-AWbVoKmcmqueLrGjRSVXjRVF0,11
+longparser-0.1.0.dist-info/RECORD,,

longparser-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

longparser-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+longparser