Merge pull request #46 from Jakedismo/claude/add-jina-embeddings-provider-011CUrSj3ypAwj1HJ88ibMcC

Add Jina as selectable embeddings provider

Author: Jakedismo

README.md

@@ -323,10 +323,18 @@ cargo build --release --bin codegraph-setup --features all-cloud-providers
 
 ### Manual Configuration
 
+**Configuration directory: `~/.codegraph/`**
+
+All configuration files are stored in `~/.codegraph/` in TOML format.
+
 Configuration is loaded from (in order):
-1. `./.codegraph.toml` (project-specific)
-2. `~/.codegraph/config.toml` (global)
-3. Environment variables
+1. `~/.codegraph/default.toml` (base configuration)
+2. `~/.codegraph/{environment}.toml` (e.g., development.toml, production.toml)
+3. `~/.codegraph/local.toml` (local overrides, machine-specific)
+4. `./config/` (fallback for backward compatibility)
+5. Environment variables (CODEGRAPH__* prefix)
+
+**See [Configuration Guide](docs/CONFIGURATION_GUIDE.md) for complete documentation.**
 
 **Full configuration example:**
 ```toml

config/README.md

@@ -0,0 +1,128 @@
+# CodeGraph Configuration Files
+
+## Important: Configuration Directory Migration
+
+**As of the latest version, CodeGraph uses `~/.codegraph` as the primary configuration directory.**
+
+### New Location: `~/.codegraph`
+
+All user-level configuration files should now be placed in:
+
+```
+~/.codegraph/
+```
+
+This provides a centralized, uniform location for all CodeGraph configuration across your system.
+
+### Why the Change?
+
+- **Centralized**: All CodeGraph configs in one place, regardless of project
+- **User-level**: Configurations follow you across different projects
+- **Standard practice**: Follows Unix/Linux convention for user configuration
+- **Cleaner projects**: Keeps project directories focused on code
+
+### Migration
+
+To migrate your existing configurations:
+
+```bash
+# Create the directory
+mkdir -p ~/.codegraph
+
+# Copy existing configs
+cp config/*.toml ~/.codegraph/
+
+# Or symlink for development (keeps backward compatibility)
+ln -s $(pwd)/config ~/.codegraph
+```
+
+### Backward Compatibility
+
+CodeGraph maintains backward compatibility by checking directories in this order:
+
+1. **`~/.codegraph/`** (Primary)
+2. **`./config/`** (This directory - fallback)
+3. **Current directory** (last resort)
+
+If `~/.codegraph` exists, it will be used. Otherwise, CodeGraph falls back to `./config/`.
+
+## Configuration Files in This Directory
+
+This directory contains **example configuration files** that can be copied to `~/.codegraph/`:
+
+- `default.toml` - Base configuration example
+- `surrealdb_example.toml` - SurrealDB configuration
+- `example_embedding.toml` - Embedding provider configuration
+- `example_performance.toml` - Performance tuning
+- `production.toml` - Production settings example
+
+## Quick Start
+
+### 1. Initialize User Config
+
+```bash
+# Create ~/.codegraph with default configs
+mkdir -p ~/.codegraph
+cp config/default.toml ~/.codegraph/
+```
+
+### 2. Customize Your Configuration
+
+```bash
+# Edit your user config
+nano ~/.codegraph/default.toml
+
+# Or create environment-specific configs
+cp ~/.codegraph/default.toml ~/.codegraph/development.toml
+cp ~/.codegraph/default.toml ~/.codegraph/production.toml
+```
+
+### 3. Set Environment
+
+```bash
+export APP_ENV=development  # Loads ~/.codegraph/development.toml
+# or
+export APP_ENV=production   # Loads ~/.codegraph/production.toml
+```
+
+## Environment Variables
+
+Override any config value using environment variables:
+
+```bash
+# Database backend
+export CODEGRAPH__DATABASE__BACKEND=surrealdb
+
+# SurrealDB connection
+export CODEGRAPH__DATABASE__SURREALDB__CONNECTION=ws://localhost:8000
+
+# Server port
+export CODEGRAPH__SERVER__PORT=8080
+```
+
+## Further Documentation
+
+- **[Full Configuration Guide](../docs/CONFIGURATION_GUIDE.md)** - Complete configuration documentation
+- **[SurrealDB Guide](../docs/SURREALDB_GUIDE.md)** - SurrealDB-specific configuration
+- **[Environment Variables](../docs/CONFIGURATION_GUIDE.md#environment-variables)** - Full list of env vars
+
+## Development
+
+For development, you can continue using this `./config` directory, but we recommend migrating to `~/.codegraph` for consistency:
+
+```bash
+# Option 1: Copy to ~/.codegraph
+mkdir -p ~/.codegraph && cp config/*.toml ~/.codegraph/
+
+# Option 2: Symlink (for active development)
+ln -s $(pwd)/config ~/.codegraph
+
+# Option 3: Keep using ./config (backward compatible)
+# CodeGraph will use ./config if ~/.codegraph doesn't exist
+```
+
+## Need Help?
+
+- Check the [Configuration Guide](../docs/CONFIGURATION_GUIDE.md)
+- See example configs in this directory
+- Use `CODEGRAPH__LOGGING__LEVEL=debug` to see which config directory is being used

config/default.toml

@@ -4,10 +4,30 @@ env = "development"
 host = "0.0.0.0"
 port = 3000
 
-[rocksdb]
+# Database configuration
+[database]
+# Backend options: "rocksdb" (default), "surrealdb"
+backend = "rocksdb"
+
+[database.rocksdb]
 path = "data/graph.db"
 read_only = false
 
+[database.surrealdb]
+# Example SurrealDB configuration (uncomment to use)
+# connection = "ws://localhost:8000"  # Standard SurrealDB WebSocket connection
+# namespace = "codegraph"
+# database = "graph"
+# auto_migrate = true
+# strict_mode = false
+# Alternative: file://data/surrealdb/graph.db for embedded mode
+
+# Deprecated: Legacy rocksdb configuration (use database.rocksdb instead)
+# This is kept for backward compatibility
+# [rocksdb]
+# path = "data/graph.db"
+# read_only = false
+
 [vector]
 dimension = 384
 index = "ivf_flat"

config/example_embedding.toml

@@ -14,6 +14,26 @@ api_base = "https://api.openai.com/v1"
 max_retries = 3
 timeout_secs = 30
 
+# Example Jina configuration (uncomment to use)
+# [embedding]
+# provider = "jina"
+# dimension = 1024
+# cache_enabled = true
+# cache_ttl_secs = 3600
+# normalize_embeddings = true
+#
+# [embedding.jina]
+# model = "jina-embeddings-v4"
+# api_key_env = "JINA_API_KEY"
+# api_base = "https://api.jina.ai/v1"
+# max_retries = 3
+# timeout_secs = 30
+# task = "code.query"
+# late_chunking = true
+# enable_reranking = true
+# reranking_model = "jina-reranker-v3"
+# reranking_top_n = 10
+
 [performance]
 mode = "balanced"
 

config/surrealdb_example.toml

@@ -0,0 +1,64 @@
+# CodeGraph Configuration with SurrealDB
+
+[database]
+# Select SurrealDB as the database backend
+backend = "surrealdb"
+
+# RocksDB configuration (not used when backend is surrealdb, but kept for backward compatibility)
+[database.rocksdb]
+path = "data/graph.db"
+read_only = false
+
+# SurrealDB configuration
+[database.surrealdb]
+# Connection string options:
+# - WebSocket (default): "ws://localhost:8000"
+# - Local file: "file://data/surrealdb/graph.db"
+# - Memory (testing): "mem://"
+# - Remote HTTP: "http://localhost:8000"
+# - Remote HTTPS: "https://example.com:8000"
+connection = "ws://localhost:8000"
+
+# Namespace for multi-tenancy (default: "codegraph")
+namespace = "codegraph"
+
+# Database name (default: "graph")
+database = "graph"
+
+# Optional: Authentication credentials
+# username = "root"
+# password = "root"  # Can also be set via CODEGRAPH__DATABASE__SURREALDB__PASSWORD env var
+
+# Enable strict schema validation (default: false)
+# When true, SurrealDB will enforce the defined schema strictly
+# When false, allows for schema flexibility and easier migrations
+strict_mode = false
+
+# Auto-apply migrations on startup (default: true)
+# When true, automatically runs pending migrations when connecting
+auto_migrate = true
+
+# Example: Remote SurrealDB server configuration
+# [database.surrealdb]
+# connection = "https://your-surrealdb-server.com:8000"
+# namespace = "production"
+# database = "codegraph"
+# username = "admin"
+# # Password should be set via environment variable:
+# # CODEGRAPH__DATABASE__SURREALDB__PASSWORD=your_password
+# strict_mode = true
+# auto_migrate = false
+
+[server]
+host = "0.0.0.0"
+port = 3000
+
+[vector]
+dimension = 1024
+
+[logging]
+level = "info"
+
+[security]
+require_auth = false
+rate_limit_per_minute = 1200