directory-indexer 0.0.5 → 0.0.7

package/README.md

@@ -4,25 +4,86 @@
 
 [![npm](https://img.shields.io/npm/v/directory-indexer)](https://npmjs.com/package/directory-indexer)
 [![Crates.io](https://img.shields.io/crates/v/directory-indexer)](https://crates.io/crates/directory-indexer)
+[![codecov](https://codecov.io/gh/peteretelej/directory-indexer/graph/badge.svg?token=j6aBBpfqkN)](https://codecov.io/gh/peteretelej/directory-indexer)
+[![Rust](https://img.shields.io/badge/rust-1.70+-blue.svg)](https://www.rust-lang.org)
 [![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)
 [![CI](https://github.com/peteretelej/directory-indexer/workflows/CI/badge.svg)](https://github.com/peteretelej/directory-indexer/actions)
 
-Give AI assistants semantic search across your local files. Find relevant documents based on meaning, not just filenames.
+Self-hosted semantic search for local files. Enable AI assistants to search your documents using vector embeddings and MCP integration.
 
-## Quick Start
+## Setup
+
+Directory Indexer runs locally on your machine or server. It uses an embedding provider (such as Ollama) to create vector embeddings of your files and stores them in a Qdrant vector database for fast semantic search. Both services can run remotely if needed.
+
+Setup requires two services:
+
+### 1. Qdrant Vector Database
+
+Choose one option:
+
+**Docker (recommended for most users):**
 
 ```bash
-# Install via npm
-npm install -g directory-indexer
+docker run -d --name qdrant \
+    -p 127.0.0.1:6333:6333 \
+    -v qdrant_storage:/qdrant/storage \
+    qdrant/qdrant
+```
 
-# Index your directories
-directory-indexer index ~/Documents ~/work/docs
+- This option requires [Docker](https://docs.docker.com/get-docker/)
+- Runs Qdrant on docker container, uses a named volume `qdrant_storage` for persistent storage.
 
-# Start MCP server for AI assistants
-directory-indexer serve
+**Alternative:** Install natively from [qdrant.tech](https://qdrant.tech/documentation/guides/installation/)
+
+### 2. Embedding Provider
+
+Choose one option:
+
+**Option A: Ollama (recommended - free, runs locally)**
+
+```bash
+# Install Ollama
+curl -fsSL https://ollama.ai/install.sh | sh  # Linux/macOS
+# For Windows: Download from https://ollama.ai
+
+# Pull the embedding model
+ollama pull nomic-embed-text
 ```
 
-**Configure with Claude Desktop:**
+- You can also [run Ollama via Docker](https://ollama.com/blog/ollama-is-now-available-as-an-official-docker-image)
+  - GPU support may require additional configuration
+
+**Option B: OpenAI (requires paid API key)**
+
+```bash
+export OPENAI_API_KEY="your-api-key-here"
+```
+
+### Quick Verification
+
+Test your setup:
+
+```bash
+# Check Qdrant
+curl http://localhost:6333/collections
+
+# Check Ollama
+curl http://localhost:11434/api/tags
+```
+
+If either fails, directory-indexer will show a helpful error with setup guidance.
+
+## Installation
+
+```bash
+npm install -g directory-indexer
+```
+
+## Usage
+
+### MCP Integration
+
+Configure with Claude Desktop:
 
 ```json
 {
@@ -35,39 +96,38 @@ directory-indexer serve
 }
 ```
 
-Now ask Claude: _"Find files similar to my Redis incident reports"_ and it will search your indexed documents semantically.
-
-## Requirements
-
-- **Qdrant**: Vector database for semantic search
+Start the MCP server:
 
 ```bash
-docker run -d --name qdrant \
-    -p 127.0.0.1:6333:6333 \
-    -v qdrant_storage:/qdrant/storage \
-    qdrant/qdrant
+directory-indexer serve
 ```
 
-**Embedding Provider** (choose one):
+Your AI assistant (Claude, Cline, Copilot, etc.) can now search your indexed documents semantically. Ask: _"Find API authentication examples"_, _"Show me incidents similar to this"_, or _"Find troubleshooting guides on SQL deadlocks"_.
 
-- **Ollama** (recommended): Self-hosted embeddings
+### CLI Commands
 
 ```bash
-# Install Ollama natively for GPU support (recommended)
-curl -fsSL https://ollama.ai/install.sh | sh
-# Visit https://ollama.ai for Windows installer
-ollama pull nomic-embed-text
+# Index your directories
+# Linux/macOS
+directory-indexer index /home/user/projects/api-docs /mnt/work/incident-reports
+# Windows
+directory-indexer index "C:\work\documentation" "D:\projects\my-app\docs"
 
-# OR use Docker (CPU-only, slower)
-docker run -d --name ollama \
-    -p 127.0.0.1:11434:11434 \
-    -v ollama_data:/root/.ollama \
-    ollama/ollama
+# Search semantically
+directory-indexer search "database timeout errors"
 
-docker exec ollama ollama pull nomic-embed-text
-```
+# Find similar files
+# Linux/macOS
+directory-indexer similar /mnt/work/incident-reports/redis-outage.md
+# Windows
+directory-indexer similar "C:\work\incidents\redis-outage.md"
 
-- **OpenAI**: Requires API key
+# Get file content
+directory-indexer get /home/user/projects/api-docs/auth-guide.md
+
+# Show status
+directory-indexer status
+```
 
 ## Configuration
 
@@ -78,8 +138,11 @@ Directory Indexer uses environment variables for configuration. Set these if you
 export QDRANT_ENDPOINT="http://localhost:6333"
 export OLLAMA_ENDPOINT="http://localhost:11434"
 
-# Optional database path (default: ~/.directory-indexer/data.db)
-export DIRECTORY_INDEXER_DB="/path/to/your/database.db"
+# Optional data directory (default: ~/.directory-indexer)
+# Linux/macOS
+export DIRECTORY_INDEXER_DATA_DIR="/opt/directory-indexer-data"
+# Windows
+set DIRECTORY_INDEXER_DATA_DIR=D:\data\directory-indexer
 
 # Optional Qdrant collection name (default: directory-indexer)
 # Note: Setting to "test" enables auto-cleanup for testing
@@ -101,32 +164,13 @@ export OLLAMA_API_KEY="your-ollama-key"  # if using hosted Ollama
       "env": {
         "QDRANT_ENDPOINT": "http://localhost:6333",
         "OLLAMA_ENDPOINT": "http://localhost:11434",
-        "DIRECTORY_INDEXER_DB": "/path/to/your/database.db"
+        "DIRECTORY_INDEXER_DATA_DIR": "/opt/directory-indexer-data"
       }
     }
   }
 }
 ```
 
-## CLI Usage
-
-```bash
-# Index your directories
-directory-indexer index ~/Documents ~/work/docs
-
-# Search semantically
-directory-indexer search "database timeout errors"
-
-# Find similar files
-directory-indexer similar ~/incidents/redis-outage.md
-
-# Get file content
-directory-indexer get ~/docs/api-guide.md
-
-# Show status
-directory-indexer status
-```
-
 ## Supported Files
 
 - **Text**: `.md`, `.txt`
@@ -140,6 +184,25 @@ directory-indexer status
 - **[Contributing](docs/CONTRIBUTING.md)**: Development setup and guidelines
 - **[Design](docs/design.md)**: Architecture and technical decisions
 
+## Usage Examples
+
+Once indexed, try these queries with your AI assistant:
+
+**Search by concept:**
+- _"Find API authentication examples"_
+- _"Show me error handling patterns"_
+- _"Find configuration for Redis"_
+
+**Find similar content:**
+- _"Show me incidents similar to this outage report"_ *(when you have an incident file open)*
+- _"Find documentation like this API guide"_ *(when viewing an API doc)*
+- _"What files are similar to my deployment script?"_
+
+**Troubleshoot issues:**
+- _"Find troubleshooting guides on SQL deadlocks"_
+- _"Show me solutions for timeout errors"_
+- _"Find debugging tips for performance issues"_
+
 ## License
 
 MIT

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "directory-indexer",
-  "version": "0.0.5",
+  "version": "0.0.7",
   "description": "AI-powered directory indexing with semantic search for MCP servers",
   "main": "bin/directory-indexer.js",
   "bin": {

package/scripts/pre-push

@@ -13,6 +13,21 @@ if [ ! -f "Cargo.toml" ]; then
     exit 1
 fi
 
+echo "Checking version synchronization..."
+# Extract version from Cargo.toml
+CARGO_VERSION=$(grep '^version = ' Cargo.toml | head -1 | sed 's/version = "\(.*\)"/\1/')
+
+# Extract version from package.json
+NPM_VERSION=$(grep '"version":' package.json | head -1 | sed 's/.*"version": "\(.*\)".*/\1/')
+
+if [ "$CARGO_VERSION" != "$NPM_VERSION" ]; then
+    echo "ERROR: Version mismatch detected!"
+    echo "  Cargo.toml version: $CARGO_VERSION"
+    echo "  package.json version: $NPM_VERSION"
+    echo "  Please ensure both files have the same version."
+    exit 1
+fi
+
 echo "Running clippy (linter)..."
 # Check main library code with strict linting
 cargo clippy --lib --all-features -- -D warnings -D clippy::uninlined_format_args
@@ -22,11 +37,12 @@ cargo clippy --bins --all-features -- -D warnings
 echo "Checking code formatting..."
 cargo fmt --check
 
-echo "Running essential tests..."
-# Only run fast, essential tests - skip the slow integration tests
+echo "Running tests..."
+export DIRECTORY_INDEXER_DATA_DIR=/tmp/directory-indexer-test
+export DIRECTORY_INDEXER_QDRANT_COLLECTION=directory-indexer-test
+
 cargo test --lib
-cargo test --test error_scenarios_tests  
-cargo test --test storage_tests
+cargo test tests
 
 echo "Checking for security vulnerabilities..."
 if command -v cargo-audit >/dev/null 2>&1; then