All 108 Dependencies

Every package Morphik depends on, ranked by repo health score.

Morphik is an AI-native ingestion and retrieval platform built for documents that don't reduce cleanly to plain text — scanned PDFs, technical manuals with diagrams, slide decks, spreadsheets, and video. Instead of assembling a pipeline out of a separate OCR tool, embedding model, and vector database, Morphik bundles ingestion, multimodal embedding, storage, and retrieval into one FastAPI-based service that developers call through a Python SDK, a REST API, or the Model Context Protocol.

Its ingestion pipeline (core/services/ingestion_service.py, core/parser/morphik_parser.py) parses files with Docling and PyMuPDF, then represents pages using the ColPali technique — patch-level image embeddings that capture the layout of a chart, table, or diagram directly, rather than flattening it into lossy OCR text. Rules-based metadata extraction runs alongside ingestion to pull out bounding boxes, labels, and classifications. Everything is stored in Postgres with pgvector, using dedicated multi-vector store implementations (core/vector_store/multi_vector_store.py, fast_multivector_store.py) to handle the many-vectors-per-page shape that ColPali produces, and heavy ingestion work is offloaded to Redis-backed background workers (arq) so the API stays responsive.

A custom Rust extension (morphik_rust, built with PyO3) handles the CPU-bound parts of the pipeline — base64 encoding, text chunking with overlap, and binary quantization / Hamming-distance search over embeddings — to keep large ingestion batches fast without leaving Python. LiteLLM sits behind the embedding and completion layers, so teams can point Morphik at OpenAI, Anthropic, Google, or a local Ollama model without changing application code.

Morphik can be self-hosted via Docker Compose (Postgres/pgvector, Redis, the API, and an ingestion worker) or run as a managed Morphik Cloud service with a free tier. The core codebase ships under the Business Source License 1.1 — a source-available license, not an OSI-approved open source one — and a separate, stricter Enterprise license covers the Google Drive, GitHub, and Zotero connectors; see the Enterprise & Self-Hosting section below for exactly what that means in practice.

16 importlib >=1.0.4 34 tailwindcss-animate ^1.0.7 39 SnakeViz >=2.2.0 40 remark-gfm ^4.0.1 40 toml >=0.10.2 42 Tailwind CSS Container Queries ^0.1.1 42 clsx ^2.1.1 44 filetype.py >=1.2.0 45 next-themes ^0.4.6 46 itsdangerous >=2.2.0 47 SheetJS (xlsx-republish) ^0.2.0 outdated 48 pdf2image >=1.16.0 48 psycopg2 >=2.9.9 50 React Syntax Highlighter ^15.6.1 outdated 50 tomli >=2.2.1 50 Yappi >=1.6.0 51 types-boto3 >=1.39.1 52 asyncpg >=0.30.0 55 arq >=0.26.3 55 HTTPX >=0.28.1 62 PyJWT >=2.0.0 64 eslint-plugin-prettier ^5.4.0 65 react-markdown ^10.1.0 66 python-multipart >=0.0.20 67 ollama-python >=0.4.8 67 pgvector-python >=0.4.1 67 rayon 1.10 68 base64 0.22 outdated 68 prettier-plugin-tailwindcss ^0.6.11 outdated 69 eslint-config-prettier ^10.1.2 74 turbopuffer-python >=1.10.0 75 torchaudio ==2.8.0 outdated 76 Radix UI ^1.1.2 76 Radix UI ^1.2.3 76 Radix UI ^1.1.10 76 Radix UI ^1.1.5 76 Radix UI ^1.1.7 76 Radix UI ^2.1.7 outdated 76 Radix UI ^2.1.2 outdated 76 Radix UI ^1.1.3 76 Radix UI ^1.2.4 76 Radix UI ^1.2.2 76 Radix UI ^2.1.7 outdated 76 Radix UI ^1.2.3 76 Radix UI ^1.1.1 76 Radix UI ^1.1.3 76 Radix UI ^1.1.2 76 Radix UI ^1.2.7 76 line_profiler >=4.1.2 76 rust-numpy 0.22 outdated 81 Psycopg >=3.2.9 81 Psycopg >=3.2.9 81 Psycopg >=3.2.6 82 AssemblyAI Python SDK >=0.40.2 83 class-variance-authority ^0.7.1 83 greenlet >=3.2.2 83 Pyzotero >=1.6.11 83 Requests >=2.32.3 85 ty >=0.0.1a6 87 Docling >=2.15.0 87 React-PDF ^9.2.1 outdated 88 build >=1.2.2.post1 88 Google API Python Client >=2.169.0 88 tailwind-merge ^2.6.0 outdated 88 WeasyPrint >=61.2 89 instructor >=1.8.1 89 lxml >=5.2.2 89 pydantic-settings >=2.9.1 89 sharp ^0.34.1 outdated 90 Tabler Icons React ^3.34.0 90 boto3 >=1.38.14 90 prettier ^3.5.3 90 PyMuPDF ==1.25.5 outdated 90 shadcn ^2.4.0-canary.11 outdated 90 Tailwind CSS ^3.4.1 outdated 90 tqdm >=4.67.1 90 Uvicorn >=0.34.2 91 FastAPI >=0.115.12 91 lucide-react ^0.469.0 outdated 91 PyO3 0.22 outdated 91 pytest-asyncio >=0.26.0 92 LiteLLM >=1.69.1 92 Pillow >=10.4.0 92 postcss ^8.5.3 92 Pydantic >=2.11.4 92 Stripe Python >=12.1.0 93 Google Gen AI Python SDK >=1.15.0 93 OpenTelemetry Prometheus Exporter >=1.33.0 outdated 93 SQLAlchemy >=2.0.40 94 ESLint ^8 outdated 94 PDF.js ^5.3.31 outdated 95 Anthropic Python SDK >=0.51.0 95 OpenAI ^4.28.4 outdated 95 OpenAI Python SDK >=1.75.0 95 vision ==0.23.0 outdated 96 Next.js 14.2.16 outdated 96 Next.js ^14 outdated 96 NumPy >=1.19.0 96 OpenTelemetry Instrumentation for kafka-python >=0.54b0 96 pytest >=8.3.5 96 sentry-sdk >=2.33.0 96 PyTorch ==2.8.0 outdated 96 TypeScript ^5.8.3 outdated 97 google-auth >=2.40.1 97 google-auth >=1.2.2 97 React ^18 outdated 97 React DOM ^18 outdated 98 Protocol Buffers >=3.19.0

All 108 Dependencies

Join founders buildingwith open source

Search