feat: support for pgvectorscale (DiskANN)

docker/docker-compose/timescale/.dockerignore

@@ -0,0 +1,16 @@
+# Git
+.git
+.gitignore
+.gitattributes
+
+# Docker
+docker-compose.yaml
+.dockerignore
+
+# Documentation
+README.md
+*.md
+
+# Environment
+.env
+.env.example

docker/docker-compose/timescale/.env.example

@@ -0,0 +1,25 @@
+# PostgreSQL Configuration
+HINDSIGHT_DB_USER=hindsight_user
+HINDSIGHT_DB_PASSWORD=change-me-to-secure-password
+HINDSIGHT_DB_NAME=hindsight_db
+
+# Hindsight Version
+HINDSIGHT_VERSION=latest
+
+# LLM Configuration
+HINDSIGHT_API_LLM_PROVIDER=openai
+OPENAI_API_KEY=your-openai-api-key-here
+
+# Alternative LLM providers (uncomment and configure as needed):
+# HINDSIGHT_API_LLM_PROVIDER=anthropic
+# ANTHROPIC_API_KEY=your-anthropic-api-key
+
+# HINDSIGHT_API_LLM_PROVIDER=gemini
+# GEMINI_API_KEY=your-gemini-api-key
+
+# HINDSIGHT_API_LLM_PROVIDER=groq
+# GROQ_API_KEY=your-groq-api-key
+
+# Vector and Text Search (already configured in docker-compose.yaml)
+# HINDSIGHT_API_VECTOR_EXTENSION=pgvectorscale
+# HINDSIGHT_API_TEXT_SEARCH_EXTENSION=pg_textsearch

docker/docker-compose/timescale/Dockerfile

@@ -0,0 +1,55 @@
+# PostgreSQL with pgvector, pgvectorscale, and pg_textsearch extensions
+# All three extensions from Timescale/pgvector for high-performance vector and text search
+# Note: Requires PostgreSQL 16+
+FROM postgres:17
+
+# Install build dependencies and Rust toolchain
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    git \
+    postgresql-server-dev-17 \
+    libpq-dev \
+    cmake \
+    curl \
+    pkg-config \
+    libssl-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Rust toolchain (required for pgvectorscale)
+RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
+ENV PATH="/root/.cargo/bin:${PATH}"
+
+# Install pgvector (required by pgvectorscale)
+RUN cd /tmp && \
+    git clone --branch v0.8.0 https://github.com/pgvector/pgvector.git && \
+    cd pgvector && \
+    make && \
+    make install && \
+    rm -rf /tmp/pgvector
+
+# Install cargo-pgrx (PostgreSQL extension framework for Rust)
+RUN cargo install cargo-pgrx --version 0.12.5 --locked && \
+    cargo pgrx init --pg17 /usr/bin/pg_config
+
+# Install pgvectorscale (DiskANN index support)
+RUN cd /tmp && \
+    git clone --branch 0.5.1 https://github.com/timescale/pgvectorscale.git && \
+    cd pgvectorscale/pgvectorscale && \
+    cargo pgrx install --release && \
+    rm -rf /tmp/pgvectorscale
+
+# Install pg_textsearch (BM25 text search)
+RUN cd /tmp && \
+    git clone https://github.com/timescale/pg_textsearch.git && \
+    cd pg_textsearch && \
+    make && \
+    make install && \
+    rm -rf /tmp/pg_textsearch
+
+# Clean up build dependencies (keep runtime dependencies)
+RUN apt-get purge -y --auto-remove git cmake curl && \
+    rm -rf /root/.cargo/registry /root/.cargo/git
+
+# Ensure extensions are preloaded (pg_textsearch requires preloading)
+RUN echo "shared_preload_libraries = 'pg_textsearch'" >> /usr/share/postgresql/postgresql.conf.sample
+

docker/docker-compose/timescale/README.md

@@ -0,0 +1,101 @@
+# Hindsight with Timescale Extensions
+
+This Docker Compose setup provides a complete Hindsight deployment with **Timescale extensions**:
+- **pgvectorscale** - DiskANN algorithm for disk-based scalable vector search  
+- **pg_textsearch** - High-performance BM25 text search
+
+Both extensions are from [Timescale](https://github.com/timescale) and provide production-grade performance.
+
+## Prerequisites
+
+- Docker and Docker Compose installed
+- OpenAI API key (or another LLM provider)
+
+## Quick Start
+
+```bash
+# Set environment variables
+export HINDSIGHT_DB_PASSWORD="your-secure-password"
+export OPENAI_API_KEY="your-openai-api-key"
+
+# Build and start
+docker compose -f docker/docker-compose/timescale/docker-compose.yaml up -d --build
+
+# Check logs
+
+docker compose -f docker/docker-compose/timescale/docker-compose.yaml logs -f
+```
+
+**Access:**
+- API: http://localhost:8888
+- Control Plane: http://localhost:9999
+
+## Stop and Clean Up
+
+```bash
+# Stop services
+docker compose -f docker/docker-compose/timescale/docker-compose.yaml down
+
+# Remove volumes (deletes all data)
+docker compose -f docker/docker-compose/timescale/docker-compose.yaml down -v
+```
+
+## Configuration
+
+### Environment Variables
+
+| Variable | Description | Default |
+|----------|-------------|---------|
+| `HINDSIGHT_DB_PASSWORD` | PostgreSQL password | `hindsight_password` |
+| `HINDSIGHT_DB_USER` | PostgreSQL username | `hindsight_user` |
+| `HINDSIGHT_DB_NAME` | Database name | `hindsight_db` |
+| `HINDSIGHT_VERSION` | Hindsight Docker image version | `latest` |
+| `OPENAI_API_KEY` | OpenAI API key | (required) |
+| `HINDSIGHT_API_LLM_PROVIDER` | LLM provider | `openai` |
+
+### Why Timescale Extensions?
+
+**pgvectorscale (DiskANN):**
+- 28x lower p95 latency vs dedicated vector databases
+- 16x higher query throughput at 99% recall
+- 60-75% cost reduction (disk is cheaper than RAM)
+- Best for large datasets (10M+ vectors)
+
+**pg_textsearch (BM25):**
+- High-performance keyword retrieval
+- Native BM25 ranking algorithm
+- Optimized for full-text search
+
+## Troubleshooting
+
+### Extensions not installed
+
+Check if extensions are available:
+
+```bash
+docker exec -it hindsight-db-timescale psql -U hindsight_user -d hindsight_db -c "\dx"
+```
+
+You should see:
+- `vector` (pgvector)
+- `vectorscale` (pgvectorscale/DiskANN)
+- `pg_textsearch` (BM25 search)
+
+### Build fails
+
+If the Docker build fails during pgvectorscale compilation:
+
+1. Ensure you have sufficient memory (recommended: 4GB+)
+2. Check Docker build logs for Rust compilation errors
+3. Try building with more resources: `docker compose build --no-cache --memory 4g`
+
+### Port conflicts
+
+If port 5438 is already in use, modify the `ports` section in docker-compose.yaml.
+
+## Learn More
+
+- [pgvectorscale GitHub](https://github.com/timescale/pgvectorscale)
+- [pg_textsearch GitHub](https://github.com/timescale/pg_textsearch)
+- [HNSW vs DiskANN](https://www.tigerdata.com/learn/hnsw-vs-diskann)
+- [Hindsight Documentation](https://hindsight.dev)

docker/docker-compose/timescale/docker-compose.yaml

@@ -0,0 +1,108 @@
+name: hindsight
+# Docker Compose file for Hindsight with Timescale extensions
+# - pgvectorscale: DiskANN vector search (disk-based, scalable)
+# - pg_textsearch: BM25 text search (high-performance keyword retrieval)
+#
+# Quick start:
+# docker compose -f docker/docker-compose/timescale/docker-compose.yaml up -d --build
+#
+# Required environment variables:
+# - HINDSIGHT_DB_PASSWORD: Password for the PostgreSQL user
+# - OPENAI_API_KEY (or configure another LLM provider)
+#
+# Optional environment variables with defaults:
+# - HINDSIGHT_VERSION: Hindsight application version (default: latest)
+# - HINDSIGHT_DB_USER: PostgreSQL user (default: hindsight_user)
+# - HINDSIGHT_DB_NAME: PostgreSQL database name (default: hindsight_db)
+
+services:
+  db:
+    # Custom PostgreSQL image with Timescale extensions (pgvectorscale + pg_textsearch)
+    build:
+      context: .
+      dockerfile: Dockerfile
+    container_name: hindsight-db-timescale
+    restart: always
+    # Expose PostgreSQL port (using 5438 to avoid conflicts with other setups)
+    ports:
+      - "5438:5432"
+    environment:
+      POSTGRES_USER: ${HINDSIGHT_DB_USER:-hindsight_user}
+      POSTGRES_PASSWORD: ${HINDSIGHT_DB_PASSWORD:-hindsight_password}
+      POSTGRES_DB: ${HINDSIGHT_DB_NAME:-hindsight_db}
+    volumes:
+      - pg_data:/var/lib/postgresql/data
+    networks:
+      - hindsight-net
+    # Health check to ensure database is ready
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U hindsight_user"]
+      interval: 5s
+      timeout: 5s
+      retries: 5
+
+  timescale-init:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    depends_on:
+      db:
+        condition: service_healthy
+    environment:
+      - PGPASSWORD=${HINDSIGHT_DB_PASSWORD:-hindsight_password}
+    command: >
+      bash -c "
+        echo 'PostgreSQL is ready - creating hindsight_db database';
+        psql -h hindsight-db-timescale -p 5432 -U hindsight_user -c 'CREATE DATABASE hindsight_db;' 2>/dev/null || echo 'Database already exists';
+        echo 'Installing Timescale extensions...';
+        echo '1/3: Installing pgvector (required by pgvectorscale)...';
+        psql -h hindsight-db-timescale -p 5432 -U hindsight_user -d hindsight_db -c 'CREATE EXTENSION IF NOT EXISTS vector CASCADE;';
+        echo '2/3: Installing pgvectorscale (DiskANN vector search)...';
+        psql -h hindsight-db-timescale -p 5432 -U hindsight_user -d hindsight_db -c 'CREATE EXTENSION IF NOT EXISTS vectorscale CASCADE;';
+        echo '3/3: Installing pg_textsearch (BM25 text search)...';
+        psql -h hindsight-db-timescale -p 5432 -U hindsight_user -d hindsight_db -c 'CREATE EXTENSION IF NOT EXISTS pg_textsearch CASCADE;';
+        echo '';
+        echo '✅ Timescale extensions installed successfully';
+        echo '';
+        echo 'Installed extensions:';
+        psql -h hindsight-db-timescale -p 5432 -U hindsight_user -d hindsight_db -c \"\\dx\" | grep -E '(vector|vectorscale|pg_textsearch)';
+      "
+    restart: "no"
+    networks:
+      - hindsight-net
+
+  hindsight:
+    image: ghcr.io/vectorize-io/hindsight:${HINDSIGHT_VERSION:-latest}
+    container_name: hindsight-app-timescale
+    ports:
+      - "8888:8888"
+      - "9999:9999"
+    environment:
+      # LLM Configuration
+      HINDSIGHT_API_LLM_PROVIDER: ${HINDSIGHT_API_LLM_PROVIDER:-openai}
+      HINDSIGHT_API_LLM_API_KEY: ${OPENAI_API_KEY:-your-api-key}
+
+      # Database Configuration
+      HINDSIGHT_API_DATABASE_URL: postgresql://${HINDSIGHT_DB_USER:-hindsight_user}:${HINDSIGHT_DB_PASSWORD:-hindsight_password}@db:5432/${HINDSIGHT_DB_NAME:-hindsight_db}
+
+      # Timescale Extensions
+      # pgvectorscale: DiskANN algorithm for disk-based scalable vector search
+      HINDSIGHT_API_VECTOR_EXTENSION: pgvectorscale
+      # pg_textsearch: High-performance BM25 text search
+      HINDSIGHT_API_TEXT_SEARCH_EXTENSION: pg_textsearch
+
+    depends_on:
+      db:
+        condition: service_healthy
+      timescale-init:
+        condition: service_completed_successfully
+    networks:
+      - hindsight-net
+
+
+networks:
+  hindsight-net:
+    driver: bridge
+
+volumes:
+  pg_data:

hindsight-api/hindsight_api/alembic/versions/5a366d414dce_initial_schema.py

@@ -24,14 +24,27 @@
 
 def _detect_vector_extension() -> str:
     """
-    Detect or validate vector extension: 'vchord' or 'pgvector'.
+    Detect or validate vector extension: 'pgvector', 'vchord', or 'pgvectorscale'.
     Respects HINDSIGHT_API_VECTOR_EXTENSION env var if set.
     """
     conn = op.get_bind()
     vector_extension = os.getenv("HINDSIGHT_API_VECTOR_EXTENSION", "pgvector").lower()
 
     # Validate configured extension is installed
-    if vector_extension == "vchord":
+    if vector_extension == "pgvectorscale":
+        # pgvectorscale requires pgvector
+        pgvector_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'vector'")).scalar()
+        if not pgvector_check:
+            raise RuntimeError(
+                "pgvectorscale requires pgvector. Install with: CREATE EXTENSION vector; CREATE EXTENSION vectorscale CASCADE;"
+            )
+        vectorscale_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'vectorscale'")).scalar()
+        if not vectorscale_check:
+            raise RuntimeError(
+                "Configured vector extension 'pgvectorscale' not found. Install it with: CREATE EXTENSION vectorscale CASCADE;"
+            )
+        return "pgvectorscale"
+    elif vector_extension == "vchord":
         vchord_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'vchord'")).scalar()
         if not vchord_check:
             raise RuntimeError(
@@ -46,7 +59,9 @@ def _detect_vector_extension() -> str:
             )
         return "pgvector"
     else:
-        raise ValueError(f"Invalid HINDSIGHT_API_VECTOR_EXTENSION: {vector_extension}. Must be 'pgvector' or 'vchord'")
+        raise ValueError(
+            f"Invalid HINDSIGHT_API_VECTOR_EXTENSION: {vector_extension}. Must be 'pgvector', 'vchord', or 'pgvectorscale'"
+        )
 
 
 def _detect_text_search_extension() -> str:
@@ -289,7 +304,14 @@ def upgrade() -> None:
     # Create vector index - conditional based on available extension
     vector_ext = _detect_vector_extension()
 
-    if vector_ext == "vchord":
+    if vector_ext == "pgvectorscale":
+        # Use DiskANN index for pgvectorscale (disk-based, scalable)
+        op.execute("""
+            CREATE INDEX idx_memory_units_embedding ON memory_units
+            USING diskann (embedding vector_cosine_ops)
+            WITH (num_neighbors = 50)
+        """)
+    elif vector_ext == "vchord":
         # Use vchordrq index for vchord (supports high-dimensional embeddings)
         op.execute("""
             CREATE INDEX idx_memory_units_embedding ON memory_units