docpipe-sdk 0.1.0__tar.gz

docpipe_sdk-0.1.0/.github/dependabot.yml

@@ -0,0 +1,35 @@
+version: 2
+
+updates:
+  # Python dependencies
+  - package-ecosystem: pip
+    directory: "/"
+    schedule:
+      interval: weekly
+      day: monday
+    open-pull-requests-limit: 10
+    labels:
+      - "dependencies"
+      - "python"
+    groups:
+      langchain:
+        patterns:
+          - "langchain-*"
+        update-types:
+          - "minor"
+          - "patch"
+      docling:
+        patterns:
+          - "docling*"
+      langextract:
+        patterns:
+          - "langextract*"
+
+  # GitHub Actions
+  - package-ecosystem: github-actions
+    directory: "/"
+    schedule:
+      interval: weekly
+    labels:
+      - "dependencies"
+      - "ci"

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

@@ -0,0 +1,35 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
+
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v6
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: pip install -e ".[dev]"
+
+      - name: Lint with ruff
+        run: ruff check src/
+
+      - name: Run unit tests
+        run: pytest tests/unit/ -v --tb=short
+
+      - name: Check types with mypy
+        run: mypy src/docpipe/ --ignore-missing-imports
+        continue-on-error: true

docpipe_sdk-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,48 @@
+name: Publish to PyPI
+
+on:
+  push:
+    tags:
+      - "v*"
+
+permissions:
+  id-token: write
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Set up Python
+        uses: actions/setup-python@v6
+        with:
+          python-version: "3.12"
+
+      - name: Install build tools
+        run: pip install build
+
+      - name: Build package
+        run: python -m build
+
+      - name: Upload artifacts
+        uses: actions/upload-artifact@v7
+        with:
+          name: dist
+          path: dist/
+
+  publish:
+    needs: build
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write
+    steps:
+      - name: Download artifacts
+        uses: actions/download-artifact@v8
+        with:
+          name: dist
+          path: dist/
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

docpipe_sdk-0.1.0/.gitignore

@@ -0,0 +1,18 @@
+__pycache__/
+*.py[cod]
+*$py.class
+*.egg-info/
+dist/
+build/
+.eggs/
+*.egg
+.venv/
+venv/
+.env
+*.so
+.mypy_cache/
+.pytest_cache/
+.ruff_cache/
+htmlcov/
+.coverage
+*.log

docpipe_sdk-0.1.0/CHANGELOG.md

@@ -0,0 +1,27 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [Unreleased]
+
+## [0.1.0] - 2026-04-04
+
+### Added
+
+- Core pipeline architecture with Protocol-based parser and extractor interfaces
+- Docling parser adapter for document parsing (PDF, DOCX, images, audio, video)
+- LangExtract extractor adapter for LLM-based structured extraction
+- LangChain extractor adapter using `with_structured_output()`
+- Ingestion pipeline with LangChain text splitters, embeddings, and PGVector
+- Plugin registry with `importlib.metadata` entry-point auto-discovery
+- Configuration via Pydantic Settings (env vars + YAML files)
+- CLI commands: `parse`, `extract`, `run`, `ingest`, `search`, `serve`, `plugins`, `config`
+- FastAPI server with REST endpoints for all pipeline operations
+- Dockerfile for containerized deployment
+- 34 unit tests with mock parser/extractor
+
+[Unreleased]: https://github.com/thesunnysinha/docpipe/compare/v0.1.0...HEAD
+[0.1.0]: https://github.com/thesunnysinha/docpipe/releases/tag/v0.1.0

docpipe_sdk-0.1.0/Dockerfile

@@ -0,0 +1,19 @@
+FROM python:3.12-slim
+
+WORKDIR /app
+
+# Install system dependencies for document processing
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    libgl1 \
+    libglib2.0-0 \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY pyproject.toml README.md LICENSE ./
+COPY src/ ./src/
+
+RUN pip install --no-cache-dir ".[all,server]"
+
+ENTRYPOINT ["docpipe"]
+CMD ["serve", "--host", "0.0.0.0", "--port", "8000"]
+
+EXPOSE 8000

docpipe_sdk-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Sunny Sinha
+
+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.

docpipe_sdk-0.1.0/PKG-INFO

@@ -0,0 +1,170 @@
+Metadata-Version: 2.4
+Name: docpipe-sdk
+Version: 0.1.0
+Summary: Unified document parsing, structured extraction, and vector ingestion pipeline
+Project-URL: Homepage, https://docpipe.vercel.app
+Project-URL: Repository, https://github.com/thesunnysinha/docpipe
+Project-URL: Bug Tracker, https://github.com/thesunnysinha/docpipe/issues
+Project-URL: Changelog, https://github.com/thesunnysinha/docpipe/blob/main/CHANGELOG.md
+Author-email: Sunny Sinha <thesunnysinha@gmail.com>
+License-Expression: MIT
+License-File: LICENSE
+Keywords: docling,document,extraction,ingestion,langchain,langextract,llm,parsing,pipeline,rag,vector
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+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: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Text Processing
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Requires-Dist: click>=8.0
+Requires-Dist: langchain-core>=0.3
+Requires-Dist: langchain-text-splitters>=0.3
+Requires-Dist: pydantic-settings>=2.0
+Requires-Dist: pydantic>=2.0
+Requires-Dist: pyyaml>=6.0
+Provides-Extra: all
+Requires-Dist: docling>=2.0; extra == 'all'
+Requires-Dist: fastapi>=0.100; extra == 'all'
+Requires-Dist: langchain-google-genai>=2.0; extra == 'all'
+Requires-Dist: langchain-ollama>=0.3; extra == 'all'
+Requires-Dist: langchain-openai>=0.3; extra == 'all'
+Requires-Dist: langchain-postgres>=0.0.12; extra == 'all'
+Requires-Dist: langextract>=0.1; extra == 'all'
+Requires-Dist: python-multipart>=0.0.6; extra == 'all'
+Requires-Dist: uvicorn[standard]>=0.20; extra == 'all'
+Provides-Extra: dev
+Requires-Dist: httpx; extra == 'dev'
+Requires-Dist: mypy; extra == 'dev'
+Requires-Dist: pytest-asyncio>=0.21; extra == 'dev'
+Requires-Dist: pytest-cov; extra == 'dev'
+Requires-Dist: pytest>=7.0; extra == 'dev'
+Requires-Dist: ruff; extra == 'dev'
+Provides-Extra: docling
+Requires-Dist: docling>=2.0; extra == 'docling'
+Provides-Extra: google
+Requires-Dist: langchain-google-genai>=2.0; extra == 'google'
+Provides-Extra: huggingface
+Requires-Dist: langchain-huggingface>=0.1; extra == 'huggingface'
+Provides-Extra: langextract
+Requires-Dist: langextract>=0.1; extra == 'langextract'
+Provides-Extra: ollama
+Requires-Dist: langchain-ollama>=0.3; extra == 'ollama'
+Provides-Extra: openai
+Requires-Dist: langchain-openai>=0.3; extra == 'openai'
+Provides-Extra: pgvector
+Requires-Dist: langchain-postgres>=0.0.12; extra == 'pgvector'
+Provides-Extra: server
+Requires-Dist: fastapi>=0.100; extra == 'server'
+Requires-Dist: python-multipart>=0.0.6; extra == 'server'
+Requires-Dist: uvicorn[standard]>=0.20; extra == 'server'
+Description-Content-Type: text/markdown
+
+# docpipe
+
+Unified document parsing, structured extraction, and vector ingestion pipeline.
+
+## Overview
+
+docpipe connects document parsing (Docling), LLM-based structured extraction (LangExtract + LangChain), and vector ingestion (pgvector via LangChain) into a single composable pipeline.
+
+**Three independent pipelines, composable together:**
+
+1. **Parse**: Unstructured docs → parsed text/markdown (Docling)
+2. **Extract**: Text → structured entities via LLM (LangExtract or LangChain)
+3. **Ingest**: Parsed chunks → embeddings → your vector DB (LangChain + pgvector)
+
+## Install
+
+```bash
+# Core only
+pip install docpipe
+
+# With all backends
+pip install "docpipe[all]"
+
+# Pick what you need
+pip install "docpipe[docling]"              # Document parsing
+pip install "docpipe[langextract]"          # Google LangExtract
+pip install "docpipe[openai]"              # OpenAI embeddings + LLM
+pip install "docpipe[pgvector]"            # PostgreSQL vector store
+pip install "docpipe[server]"              # FastAPI server
+```
+
+## Quick Start
+
+### Python API
+
+```python
+import docpipe
+
+# Parse a document
+doc = docpipe.parse("invoice.pdf")
+print(doc.markdown)
+
+# Extract structured data
+schema = docpipe.ExtractionSchema(
+    description="Extract invoice line items with amounts",
+    model_id="gemini-2.5-flash",
+)
+results = docpipe.extract(doc.text, schema)
+
+# Full pipeline
+result = docpipe.run("invoice.pdf", schema)
+
+# Ingest into your vector DB
+config = docpipe.IngestionConfig(
+    connection_string="postgresql://user:pass@localhost:5432/mydb",
+    table_name="invoices",
+    embedding_provider="openai",
+    embedding_model="text-embedding-3-small",
+)
+docpipe.ingest("invoice.pdf", config=config)
+```
+
+### CLI
+
+```bash
+docpipe parse invoice.pdf --format markdown
+docpipe extract "John Doe, age 30" --schema schema.yaml --model gemini-2.5-flash
+docpipe run invoice.pdf --schema schema.yaml --model gemini-2.5-flash
+docpipe ingest invoice.pdf --db "postgresql://..." --table invoices \
+    --embedding-provider openai --embedding-model text-embedding-3-small
+docpipe search "total amount" --db "postgresql://..." --table invoices \
+    --embedding-provider openai --embedding-model text-embedding-3-small
+docpipe serve
+docpipe plugins list
+```
+
+### Docker
+
+```bash
+# API server
+docker run -p 8000:8000 --env-file .env docpipe
+
+# CLI
+docker run -v ./data:/data docpipe parse /data/invoice.pdf
+```
+
+## Plugin System
+
+Third-party packages can register as plugins via entry points:
+
+```toml
+# In your package's pyproject.toml
+[project.entry-points."docpipe.parsers"]
+my_parser = "my_package:MyParser"
+
+[project.entry-points."docpipe.extractors"]
+my_extractor = "my_package:MyExtractor"
+```
+
+## License
+
+MIT

docpipe_sdk-0.1.0/README.md

@@ -0,0 +1,102 @@
+# docpipe
+
+Unified document parsing, structured extraction, and vector ingestion pipeline.
+
+## Overview
+
+docpipe connects document parsing (Docling), LLM-based structured extraction (LangExtract + LangChain), and vector ingestion (pgvector via LangChain) into a single composable pipeline.
+
+**Three independent pipelines, composable together:**
+
+1. **Parse**: Unstructured docs → parsed text/markdown (Docling)
+2. **Extract**: Text → structured entities via LLM (LangExtract or LangChain)
+3. **Ingest**: Parsed chunks → embeddings → your vector DB (LangChain + pgvector)
+
+## Install
+
+```bash
+# Core only
+pip install docpipe
+
+# With all backends
+pip install "docpipe[all]"
+
+# Pick what you need
+pip install "docpipe[docling]"              # Document parsing
+pip install "docpipe[langextract]"          # Google LangExtract
+pip install "docpipe[openai]"              # OpenAI embeddings + LLM
+pip install "docpipe[pgvector]"            # PostgreSQL vector store
+pip install "docpipe[server]"              # FastAPI server
+```
+
+## Quick Start
+
+### Python API
+
+```python
+import docpipe
+
+# Parse a document
+doc = docpipe.parse("invoice.pdf")
+print(doc.markdown)
+
+# Extract structured data
+schema = docpipe.ExtractionSchema(
+    description="Extract invoice line items with amounts",
+    model_id="gemini-2.5-flash",
+)
+results = docpipe.extract(doc.text, schema)
+
+# Full pipeline
+result = docpipe.run("invoice.pdf", schema)
+
+# Ingest into your vector DB
+config = docpipe.IngestionConfig(
+    connection_string="postgresql://user:pass@localhost:5432/mydb",
+    table_name="invoices",
+    embedding_provider="openai",
+    embedding_model="text-embedding-3-small",
+)
+docpipe.ingest("invoice.pdf", config=config)
+```
+
+### CLI
+
+```bash
+docpipe parse invoice.pdf --format markdown
+docpipe extract "John Doe, age 30" --schema schema.yaml --model gemini-2.5-flash
+docpipe run invoice.pdf --schema schema.yaml --model gemini-2.5-flash
+docpipe ingest invoice.pdf --db "postgresql://..." --table invoices \
+    --embedding-provider openai --embedding-model text-embedding-3-small
+docpipe search "total amount" --db "postgresql://..." --table invoices \
+    --embedding-provider openai --embedding-model text-embedding-3-small
+docpipe serve
+docpipe plugins list
+```
+
+### Docker
+
+```bash
+# API server
+docker run -p 8000:8000 --env-file .env docpipe
+
+# CLI
+docker run -v ./data:/data docpipe parse /data/invoice.pdf
+```
+
+## Plugin System
+
+Third-party packages can register as plugins via entry points:
+
+```toml
+# In your package's pyproject.toml
+[project.entry-points."docpipe.parsers"]
+my_parser = "my_package:MyParser"
+
+[project.entry-points."docpipe.extractors"]
+my_extractor = "my_package:MyExtractor"
+```
+
+## License
+
+MIT

docpipe_sdk-0.1.0/docpipe.example.yaml

@@ -0,0 +1,29 @@
+# docpipe configuration
+# Copy to docpipe.yaml and customize
+
+# Parser settings
+default_parser: docling
+parser_options: {}
+
+# Extractor settings
+default_extractor: langextract
+extractor_options: {}
+
+# Ingestion settings (provide your own DB connection)
+# db_connection_string: postgresql://user:pass@host:5432/dbname
+# db_table_name: docpipe_documents
+# embedding_provider: openai
+# embedding_model: text-embedding-3-small
+# chunk_size: 1000
+# chunk_overlap: 200
+# ingest_mode: both
+
+# Server settings
+server_host: "0.0.0.0"
+server_port: 8000
+
+# Pipeline settings
+max_concurrency: 4
+
+# Logging
+log_level: INFO

docpipe_sdk-0.1.0/pyproject.toml

@@ -0,0 +1,100 @@
+[build-system]
+requires = ["hatchling>=1.26"]
+build-backend = "hatchling.build"
+
+[project]
+name = "docpipe-sdk"
+version = "0.1.0"
+description = "Unified document parsing, structured extraction, and vector ingestion pipeline"
+readme = "README.md"
+license = "MIT"
+license-files = ["LICENSE"]
+requires-python = ">=3.10"
+authors = [{ name = "Sunny Sinha", email = "thesunnysinha@gmail.com" }]
+keywords = ["document", "parsing", "extraction", "llm", "pipeline", "vector", "ingestion", "rag", "docling", "langextract", "langchain"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Text Processing",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Typing :: Typed",
+]
+
+dependencies = [
+    "pydantic>=2.0",
+    "pydantic-settings>=2.0",
+    "pyyaml>=6.0",
+    "click>=8.0",
+    "langchain-core>=0.3",
+    "langchain-text-splitters>=0.3",
+]
+
+[project.optional-dependencies]
+docling = ["docling>=2.0"]
+langextract = ["langextract>=0.1"]
+openai = ["langchain-openai>=0.3"]
+google = ["langchain-google-genai>=2.0"]
+ollama = ["langchain-ollama>=0.3"]
+huggingface = ["langchain-huggingface>=0.1"]
+pgvector = ["langchain-postgres>=0.0.12"]
+server = ["fastapi>=0.100", "uvicorn[standard]>=0.20", "python-multipart>=0.0.6"]
+all = ["docpipe-sdk[docling,langextract,openai,google,ollama,pgvector,server]"]
+dev = [
+    "pytest>=7.0",
+    "pytest-asyncio>=0.21",
+    "pytest-cov",
+    "ruff",
+    "mypy",
+    "httpx",
+]
+
+[project.scripts]
+docpipe = "docpipe.cli.main:cli"
+
+[project.entry-points."docpipe.parsers"]
+docling = "docpipe.parsers.docling_parser:DoclingParser"
+
+[project.entry-points."docpipe.extractors"]
+langextract = "docpipe.extractors.langextract_extractor:LangExtractExtractor"
+langchain = "docpipe.extractors.langchain_extractor:LangChainExtractor"
+
+[project.urls]
+Homepage = "https://docpipe.vercel.app"
+Repository = "https://github.com/thesunnysinha/docpipe"
+"Bug Tracker" = "https://github.com/thesunnysinha/docpipe/issues"
+Changelog = "https://github.com/thesunnysinha/docpipe/blob/main/CHANGELOG.md"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/docpipe"]
+
+[tool.ruff]
+target-version = "py310"
+line-length = 100
+src = ["src"]
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "UP", "B", "SIM"]
+
+[tool.mypy]
+python_version = "3.10"
+strict = true
+warn_return_any = true
+warn_unused_configs = true
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+asyncio_mode = "auto"
+markers = [
+    "requires_docling: needs docling installed",
+    "requires_langextract: needs langextract installed",
+    "requires_langchain: needs langchain provider installed",
+    "requires_pgvector: needs pgvector DB available",
+    "requires_api_key: needs LLM API key configured",
+]

docpipe_sdk-0.1.0/scripts/release.sh

@@ -0,0 +1,32 @@
+#!/bin/bash
+# Release script for docpipe
+# Usage: ./scripts/release.sh 0.2.0
+
+set -euo pipefail
+
+VERSION="${1:?Usage: $0 <version>}"
+
+echo "Releasing docpipe v${VERSION}..."
+
+# Update version in source
+sed -i.bak "s/__version__ = \".*\"/__version__ = \"${VERSION}\"/" src/docpipe/_version.py
+rm -f src/docpipe/_version.py.bak
+
+# Update version in pyproject.toml
+sed -i.bak "s/^version = \".*\"/version = \"${VERSION}\"/" pyproject.toml
+rm -f pyproject.toml.bak
+
+# Stage changes
+git add src/docpipe/_version.py pyproject.toml
+
+# Commit
+git commit -m "release: v${VERSION}"
+
+# Tag
+git tag -a "v${VERSION}" -m "Release v${VERSION}"
+
+echo ""
+echo "Done! To publish:"
+echo "  git push origin main --tags"
+echo ""
+echo "GitHub Actions will automatically publish to PyPI."