import docpipe

doc = docpipe.parse("invoice.pdf")
config = docpipe.IngestionConfig(
    connection_string="postgresql://user:pass@localhost:5432/mydb",
    table_name="docs",
    embedding_provider="openai",
    embedding_model="text-embedding-3-small",
)
docpipe.ingest("invoice.pdf", config=config)
result = docpipe.query("What is the invoice total?", config=docpipe.RAGConfig(
    connection_string=config.connection_string,
    table_name=config.table_name,
    embedding_provider="openai",
    embedding_model="text-embedding-3-small",
    llm_provider="openai",
    llm_model="gpt-4o",
))
print(result.answer)

pip install docpipe-sdk                        # Core only

# Curated profiles (recommended)
pip install "docpipe-sdk[profile-slim]"      # MarkItDown, fast chunking
pip install "docpipe-sdk[profile-balanced]"  # Docling, semchunk, hybrid RAG (default)
pip install "docpipe-sdk[profile-quality]"     # GLM-OCR, BGE rerank
pip install "docpipe-sdk[profile-agents]"    # Balanced + AutoGen

# À la carte
pip install "docpipe-sdk[docling]"             # Docling parser
pip install "docpipe-sdk[markitdown]"        # Lightweight Office/PDF → Markdown
pip install "docpipe-sdk[glm-ocr]"           # GLM-OCR (scanned docs)
pip install "docpipe-sdk[langextract]"       # Google LangExtract
pip install "docpipe-sdk[openai]"            # OpenAI embeddings & LLM
pip install "docpipe-sdk[pgvector]"          # PostgreSQL vector store
pip install "docpipe-sdk[turbovec]"          # On-disk vector indices
pip install "docpipe-sdk[rag]"               # Hybrid BM25 + vector
pip install "docpipe-sdk[rerank]"            # FlashRank reranker
pip install "docpipe-sdk[server]"            # FastAPI + /admin + Alembic
pip install "docpipe-sdk[observability]"     # OpenTelemetry + Prometheus
pip install "docpipe-sdk[http]"              # Python HTTP client
pip install "docpipe-sdk[all]"               # Dev/CI only

# Runtime presets (pass on /ingest, /rag/query, /agents/query)
# fast     — low latency, recursive chunks, no rerank
# balanced — default production (semchunk + flashrank)
# quality  — OCR parsers, semantic chunks, BGE rerank
# agents   — tool-using RAG via /agents/query

curl -u admin:pass http://localhost:8000/profiles
curl -u admin:pass http://localhost:8000/plugins

docpipe plugins list
docpipe profiles list
docpipe resolve invoice.pdf --goal ingest

docpipe plugins list
docpipe profiles list
docpipe resolve invoice.pdf --goal ingest

import docpipe

# Default: auto router (tier balanced) or explicit parser
doc = docpipe.parse("invoice.pdf")
print(doc.markdown)

# Lightweight Office/PDF → Markdown
doc = docpipe.parse("report.docx", parser="markitdown")

# GLM-OCR (scanned / image-heavy documents)
doc = docpipe.parse("scanned_report.pdf", parser="glm-ocr")
print(doc.markdown)

import docpipe

schema = docpipe.ExtractionSchema(
    description="Extract invoice line items with amounts",
    model_id="gemini-2.5-flash",
)
results = docpipe.extract(doc.text, schema)
for r in results:
    print(r.entity_class, r.text, r.attributes)

# Full parse + extract
result = docpipe.run("invoice.pdf", schema)
print(result.parsed.markdown)
print(result.extractions)

import docpipe

config = docpipe.IngestionConfig(
    connection_string="postgresql://user:pass@localhost:5432/mydb",
    table_name="invoices",
    embedding_provider="openai",
    embedding_model="text-embedding-3-small",
    incremental=True,  # skip unchanged files by SHA-256 hash
)
docpipe.ingest("invoice.pdf", config=config)

# API: pass preset=balanced|fast|quality on ingest for parser/chunker/rerank bundle

curl -u admin:secret -N -X POST http://localhost:8000/ingest/stream \
  -H "Content-Type: application/json" \
  -d '{
    "source": "file:///data/doc.pdf",
    "connection_string": "postgresql://user:pass@db:5432/mydb",
    "table_name": "docs",
    "embedding_provider": "openai",
    "embedding_model": "text-embedding-3-small",
    "preset": "balanced"
  }'
# SSE events: resolve → parse → chunk → complete

import docpipe

rag_config = docpipe.RAGConfig(
    connection_string="postgresql://user:pass@localhost:5432/mydb",
    table_name="invoices",
    embedding_provider="openai",
    embedding_model="text-embedding-3-small",
    llm_provider="openai",
    llm_model="gpt-4o",
    strategy="hyde",
    reranker="flashrank",
)
result = docpipe.query("What is the total amount on the invoice?", config=rag_config)
print(result.answer)
print(result.sources)
print(result.usage)  # token counts when available

from docpipe.client.integration import DocpipeClient

with DocpipeClient(
    "http://docpipe.docpipe.svc.cluster.local:8000",
    username="admin",
    password="...",
) as client:
    print(client.available_preset_names())  # fast, balanced, quality, agents
    rec = client.resolve(source="invoice.pdf", preset="balanced")
    client.ingest(
        source="s3://bucket/invoice.pdf",
        connection_string="postgresql://delegate:pass@delegate-db:5432/delegate",
        table_name="assistant_docs",
        embedding_provider="openai",
        embedding_model="text-embedding-3-small",
        preset="balanced",
    )

# pip install "docpipe-sdk[server,observability]"
DOCPIPE_OTEL_ENABLED=true
DOCPIPE_OTEL_SERVICE_NAME=docpipe
DOCPIPE_OTEL_EXPORTER_OTLP_ENDPOINT=http://otel-collector:4318/v1/traces
DOCPIPE_OTEL_TRACES_SAMPLER_ARG=1.0
DOCPIPE_LOG_FORMAT=json
DOCPIPE_HEALTH_CHECK_DB=true

$ docpipe serve

# curl http://localhost:8000/health   # plugins + dependency status
# curl http://localhost:8000/metrics # Prometheus (no auth on /metrics)

# pip install "docpipe-sdk[turbovec,openai]"   # + your embedding provider
export DOCPIPE_VECTOR_BACKEND=turbovec
export DOCPIPE_TURBVEC_INDEX_DIR=./.docpipe/indices   # default on-disk index root

# Per-request override on ingest / search / RAG API bodies:
# { "vector_backend": "turbovec", "table_name": "my_library", ... }

import docpipe

config = docpipe.IngestionConfig(
    connection_string="postgresql://unused",  # accepted; vectors use local files
    table_name="my_library",                  # index folder name under TURBVEC_INDEX_DIR
    embedding_provider="openai",
    embedding_model="text-embedding-3-small",
    vector_backend="turbovec",
)
docpipe.ingest("invoice.pdf", config=config)
# → ./.docpipe/indices/my_library/index.tvim + docstore.json

# Default pgvector in PostgreSQL is recommended for production deployments.

from docpipe.http import DocpipeClient

with DocpipeClient("http://localhost:8000", username="admin", password="docpipe") as client:
    print(client.health())
    print(client.get("/profiles").json())
    result = client.rag_query({...})
    print(result.get("usage"))

# Optional operator metadata (NOT your vector/RAG data)
DOCPIPE_CONTROL_DB_ENABLED=true
DOCPIPE_CONTROL_DB_PATH=/data/docpipe.db
DOCPIPE_ADMIN_PANEL_ENABLED=true
DOCPIPE_PERSIST_AUDIT_EVENTS=true
DOCPIPE_PERSIST_INGEST_JOBS=false
DOCPIPE_PERSIST_PLUGIN_RESOLUTIONS=false

# Admin login (seeded on first boot)
DOCPIPE_USERNAME=admin
DOCPIPE_PASSWORD=change-me

# Profile-tagged images (GHCR)
docker pull ghcr.io/thesunnysinha/docpipe:balanced
docker pull ghcr.io/thesunnysinha/docpipe:slim
docker pull ghcr.io/thesunnysinha/docpipe:quality
docker pull ghcr.io/thesunnysinha/docpipe:agents

# API server — .env: OPENAI_API_KEY, DOCPIPE_PASSWORD, etc.
docker run -p 8000:8000 --env-file .env -v ./data:/data \
  ghcr.io/thesunnysinha/docpipe:balanced

# curl -u admin:password http://localhost:8000/health
# curl -u admin:password http://localhost:8000/admin
# curl http://localhost:8000/metrics

# One-off parse / ingest
docker run -v ./data:/data ghcr.io/thesunnysinha/docpipe:balanced \
  parse /data/invoice.pdf

# Shared internal API — each app passes its own connection_string
# See: github.com/thesunnysinha/docpipe/tree/main/examples/internal-shared
services:
  docpipe:
    image: ghcr.io/thesunnysinha/docpipe:balanced
    ports:
      - "8000:8000"
    env_file: .env
    environment:
      DOCPIPE_CONTROL_DB_ENABLED: "true"
      DOCPIPE_CONTROL_DB_PATH: /data/docpipe.db
      DOCPIPE_PERSIST_AUDIT_EVENTS: "true"
      DOCPIPE_ALLOW_PRIVATE_URLS: "true"
    volumes:
      - ./data:/data
    restart: unless-stopped

# cp .env.example .env && docker compose up -d

# docpipe + pgvector — local dev
# Full examples: github.com/thesunnysinha/docpipe/tree/main/examples
services:
  docpipe:
    image: ghcr.io/thesunnysinha/docpipe:balanced
    ports:
      - "8000:8000"
    env_file: .env
    environment:
      DOCPIPE_DB_CONNECTION_STRING: postgresql://docpipe:docpipe@db:5432/docpipe
      DOCPIPE_CONTROL_DB_ENABLED: "true"
      DOCPIPE_CONTROL_DB_PATH: /data/docpipe.db
    volumes:
      - ./data:/data
    depends_on:
      db:
        condition: service_healthy
    restart: unless-stopped

  db:
    image: pgvector/pgvector:pg16
    environment:
      POSTGRES_USER: docpipe
      POSTGRES_PASSWORD: docpipe
      POSTGRES_DB: docpipe
    ports:
      - "5432:5432"
    volumes:
      - pgdata:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U docpipe"]
      interval: 5s
      timeout: 5s
      retries: 5
    restart: unless-stopped

volumes:
  pgdata:

# cp .env.example .env && docker compose up -d