fix typo in README

Merge branch 'append'
update variable name as 'gen' is a reserved keyword since Rust 2024 edition
2025-09-11 15:34:03 +02:00 · 2025-09-11 15:31:47 +02:00 · 2025-09-11 15:25:26 +02:00 · 2025-09-11 15:24:28 +02:00 · 2025-09-09 16:04:31 +02:00 · 2025-08-27 15:39:59 +02:00
50 changed files with 9661 additions and 66 deletions
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -214,9 +214,9 @@ checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"

 [[package]]
 name = "bitflags"
-version = "2.9.2"
+version = "2.9.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6a65b545ab31d687cff52899d4890855fec459eb6afe0da6417b8a18da87aa29"
+checksum = "34efbcccd345379ca2868b2b2c9d3782e9cc58ba87bc7d79d5b53d9c9ae6f25d"

 [[package]]
 name = "block-buffer"
@@ -241,9 +241,9 @@ checksum = "d71b6127be86fdcfddb610f7182ac57211d4b18a3e9c82eb2d17662f2227ad6a"

 [[package]]
 name = "cfg-if"
-version = "1.0.1"
+version = "1.0.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9555578bc9e57714c812a1f84e4fc5b4d21fcb063490c624de019f7464c91268"
+checksum = "2fd1289c04a9ea8cb22300a459a72a385d7c73d3259e2ed7dcb2af674838cfa9"

 [[package]]
 name = "chacha20"
@@ -556,9 +556,9 @@ dependencies = [

 [[package]]
 name = "form_urlencoded"
-version = "1.2.1"
+version = "1.2.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e13624c2627564efccf4934284bdd98cbaa14e79b0b5a141218e507b3a823456"
+checksum = "cb4cb245038516f5f85277875cdaa4f7d2c9a0fa0468de06ed190163b1581fcf"
 dependencies = [
 "percent-encoding",
 ]
@@ -911,9 +911,9 @@ dependencies = [

 [[package]]
 name = "idna"
-version = "1.0.3"
+version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "686f825264d630750a544639377bae737628043f20d38bbc029e8f29ea968a7e"
+checksum = "3b0875f23caa03898994f6ddc501886a45c7d3d62d04d2d90788d47be1b1e4de"
 dependencies = [
 "idna_adapter",
 "smallvec",
@@ -969,11 +969,11 @@ dependencies = [

 [[package]]
 name = "io-uring"
-version = "0.7.9"
+version = "0.7.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d93587f37623a1a17d94ef2bc9ada592f5465fe7732084ab7beefabe5c77c0c4"
+checksum = "046fa2d4d00aea763528b4950358d0ead425372445dc8ff86312b3c69ff7727b"
 dependencies = [
- "bitflags 2.9.2",
+ "bitflags 2.9.3",
 "cfg-if",
 "libc",
 ]
@@ -1159,9 +1159,9 @@ dependencies = [

 [[package]]
 name = "percent-encoding"
-version = "2.3.1"
+version = "2.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e3148f5046208a5d56bcfc03053e3ca6334e51da8dfb19b6cdc8b306fae3283e"
+checksum = "9b4f627cb1b25917193a259e49bdad08f671f8d9708acfd5fe0a8c1455d87220"

 [[package]]
 name = "pin-project"
@@ -1260,9 +1260,9 @@ dependencies = [

 [[package]]
 name = "proc-macro2"
-version = "1.0.97"
+version = "1.0.101"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d61789d7719defeb74ea5fe81f2fdfdbd28a803847077cecce2ff14e1472f6f1"
+checksum = "89ae43fd86e4158d6db51ad8e2b80f313af9cc74f5c0e03ccb87de09998732de"
 dependencies = [
 "unicode-ident",
 ]
@@ -1351,7 +1351,7 @@ version = "0.5.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5407465600fb0548f1442edf71dd20683c6ed326200ace4b1ef0763521bb3b77"
 dependencies = [
- "bitflags 2.9.2",
+ "bitflags 2.9.3",
 ]

 [[package]]
@@ -1508,9 +1508,9 @@ dependencies = [

 [[package]]
 name = "serde_json"
-version = "1.0.142"
+version = "1.0.143"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "030fedb782600dcbd6f02d479bf0d817ac3bb40d644745b769d6a96bc3afc5a7"
+checksum = "d401abef1d108fbd9cbaebc3e46611f4b1021f714a0597a71f41ee463f5f4a5a"
 dependencies = [
 "itoa",
 "memchr",
@@ -1802,9 +1802,9 @@ dependencies = [

 [[package]]
 name = "url"
-version = "2.5.4"
+version = "2.5.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "32f8b686cadd1473f4bd0117a5d28d36b1ade384ea9b5069a1c40aefed7fda60"
+checksum = "137a3c834eaf7139b73688502f3f1141a0337c5d8e4d9b536f9b8c796e26a7c4"
 dependencies = [
 "form_urlencoded",
 "idna",
@@ -1863,11 +1863,11 @@ checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"

 [[package]]
 name = "winapi-util"
-version = "0.1.9"
+version = "0.1.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cf221c93e13a30d793f7645a0e7762c55d169dbb0a49671918a2319d289b10bb"
+checksum = "0978bf7171b3d90bac376700cb56d606feb40f251a475a5d6634613564460b22"
 dependencies = [
- "windows-sys 0.59.0",
+ "windows-sys 0.60.2",
 ]

 [[package]]
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -1,9 +1,29 @@
-[workspace]
-members = ["herodb"]
-resolver = "2"
+[package]
+name = "herodb"
+version = "0.0.1"
+authors = ["ThreeFold Tech NV"]
+edition = "2024"

-# You can define shared profiles for all workspace members here
-[profile.release]
-lto = true
-codegen-units = 1
-strip = true
+[dependencies]
+anyhow = "1.0.59"
+bytes = "1.3.0"
+thiserror = "1.0.32"
+tokio = { version = "1.23.0", features = ["full"] }
+clap = { version = "4.5.20", features = ["derive"] }
+byteorder = "1.4.3"
+futures = "0.3"
+sled = "0.34"
+redb = "2.1.3"
+serde = { version = "1.0", features = ["derive"] }
+serde_json = "1.0"
+bincode = "1.3"
+chacha20poly1305 = "0.10.1"
+rand = "0.8"
+sha2 = "0.10"
+age = "0.10"
+secrecy = "0.8"
+ed25519-dalek = "2"
+base64 = "0.22"
+
+[dev-dependencies]
+redis = { version = "0.24", features = ["aio", "tokio-comp"] }
--- a/herodb/README.md
+++ b/herodb/README.md
@@ -47,13 +47,13 @@ You can start HeroDB with different backends and encryption options:
 #### `redb` with Encryption

 ```bash
-./target/release/herodb --dir /tmp/herodb_encrypted --port 6379 --encrypt --key mysecretkey
+./target/release/herodb --dir /tmp/herodb_encrypted --port 6379 --encrypt --encryption_key mysecretkey
 ```

 #### `sled` with Encryption

 ```bash
-./target/release/herodb --dir /tmp/herodb_sled_encrypted --port 6379 --sled --encrypt --key mysecretkey
+./target/release/herodb --dir /tmp/herodb_sled_encrypted --port 6379 --sled --encrypt --encryption_key mysecretkey
 ```

 ## Usage with Redis Clients
--- a/herodb/build.sh
+++ b/herodb/build.sh
--- a/herodb/docs/age.md
+++ b/herodb/docs/age.md
--- a/herodb/docs/basics.md
+++ b/herodb/docs/basics.md
--- a/herodb/docs/cmds.md
+++ b/herodb/docs/cmds.md
@@ -70,6 +70,15 @@ MULTI/EXEC/DISCARD | ✅ | ❌ | Only supported in redb |
 **Encryption** | | | |
 Data-at-rest encryption | ✅ | ✅ | Both support [age](age.tech) encryption |
 AGE commands | ✅ | ✅ | Both support AGE crypto commands |
+**Full-Text Search** | | | |
+FT.CREATE | ✅ | ✅ | Create search index with schema |
+FT.ADD | ✅ | ✅ | Add document to search index |
+FT.SEARCH | ✅ | ✅ | Search documents with query |
+FT.DEL | ✅ | ✅ | Delete document from index |
+FT.INFO | ✅ | ✅ | Get index information |
+FT.DROP | ✅ | ✅ | Drop search index |
+FT.ALTER | ✅ | ✅ | Alter index schema |
+FT.AGGREGATE | ✅ | ✅ | Aggregate search results |

 ### Performance Considerations

--- a/docs/search.md
+++ b/docs/search.md
@@ -0,0 +1,397 @@
+# Full-Text Search with Tantivy
+
+HeroDB includes powerful full-text search capabilities powered by [Tantivy](https://github.com/quickwit-oss/tantivy), a fast full-text search engine library written in Rust. This provides Redis-compatible search commands similar to RediSearch.
+
+## Overview
+
+The search functionality allows you to:
+- Create search indexes with custom schemas
+- Index documents with multiple field types
+- Perform complex queries with filters
+- Support for text, numeric, date, and geographic data
+- Real-time search with high performance
+
+## Search Commands
+
+### FT.CREATE - Create Search Index
+
+Create a new search index with a defined schema.
+
+```bash
+FT.CREATE index_name SCHEMA field_name field_type [options] [field_name field_type [options] ...]
+```
+
+**Field Types:**
+- `TEXT` - Full-text searchable text fields
+- `NUMERIC` - Numeric fields (integers, floats)
+- `TAG` - Tag fields for exact matching
+- `GEO` - Geographic coordinates (lat,lon)
+- `DATE` - Date/timestamp fields
+
+**Field Options:**
+- `STORED` - Store field value for retrieval
+- `INDEXED` - Make field searchable
+- `TOKENIZED` - Enable tokenization for text fields
+- `FAST` - Enable fast access for numeric fields
+
+**Example:**
+```bash
+# Create a product search index
+FT.CREATE products SCHEMA 
+  title TEXT STORED INDEXED TOKENIZED
+  description TEXT STORED INDEXED TOKENIZED  
+  price NUMERIC STORED INDEXED FAST
+  category TAG STORED
+  location GEO STORED
+  created_date DATE STORED INDEXED
+```
+
+### FT.ADD - Add Document to Index
+
+Add a document to a search index.
+
+```bash
+FT.ADD index_name doc_id [SCORE score] FIELDS field_name field_value [field_name field_value ...]
+```
+
+**Example:**
+```bash
+# Add a product document
+FT.ADD products product:1 SCORE 1.0 FIELDS 
+  title "Wireless Headphones" 
+  description "High-quality wireless headphones with noise cancellation"
+  price 199.99
+  category "electronics"
+  location "37.7749,-122.4194"
+  created_date 1640995200000
+```
+
+### FT.SEARCH - Search Documents
+
+Search for documents in an index.
+
+```bash
+FT.SEARCH index_name query [LIMIT offset count] [FILTER field min max] [RETURN field [field ...]]
+```
+
+**Query Syntax:**
+- Simple terms: `wireless headphones`
+- Phrase queries: `"noise cancellation"`
+- Field-specific: `title:wireless`
+- Boolean operators: `wireless AND headphones`
+- Wildcards: `head*`
+
+**Examples:**
+```bash
+# Simple text search
+FT.SEARCH products "wireless headphones"
+
+# Search with filters
+FT.SEARCH products "headphones" FILTER price 100 300 LIMIT 0 10
+
+# Field-specific search
+FT.SEARCH products "title:wireless AND category:electronics"
+
+# Return specific fields only
+FT.SEARCH products "*" RETURN title price
+```
+
+### FT.DEL - Delete Document
+
+Remove a document from the search index.
+
+```bash
+FT.DEL index_name doc_id
+```
+
+**Example:**
+```bash
+FT.DEL products product:1
+```
+
+### FT.INFO - Get Index Information
+
+Get information about a search index.
+
+```bash
+FT.INFO index_name
+```
+
+**Returns:**
+- Index name and document count
+- Field definitions and types
+- Index configuration
+
+**Example:**
+```bash
+FT.INFO products
+```
+
+### FT.DROP - Drop Index
+
+Delete an entire search index.
+
+```bash
+FT.DROP index_name
+```
+
+**Example:**
+```bash
+FT.DROP products
+```
+
+### FT.ALTER - Alter Index Schema
+
+Add new fields to an existing index.
+
+```bash
+FT.ALTER index_name SCHEMA ADD field_name field_type [options]
+```
+
+**Example:**
+```bash
+FT.ALTER products SCHEMA ADD brand TAG STORED
+```
+
+### FT.AGGREGATE - Aggregate Search Results
+
+Perform aggregations on search results.
+
+```bash
+FT.AGGREGATE index_name query [GROUPBY field] [REDUCE function field AS alias]
+```
+
+**Example:**
+```bash
+# Group products by category and count
+FT.AGGREGATE products "*" GROUPBY category REDUCE COUNT 0 AS count
+```
+
+## Field Types in Detail
+
+### TEXT Fields
+- **Purpose**: Full-text search on natural language content
+- **Features**: Tokenization, stemming, stop-word removal
+- **Options**: `STORED`, `INDEXED`, `TOKENIZED`
+- **Example**: Product titles, descriptions, content
+
+### NUMERIC Fields  
+- **Purpose**: Numeric data for range queries and sorting
+- **Types**: I64, U64, F64
+- **Options**: `STORED`, `INDEXED`, `FAST`
+- **Example**: Prices, quantities, ratings
+
+### TAG Fields
+- **Purpose**: Exact-match categorical data
+- **Features**: No tokenization, exact string matching
+- **Options**: `STORED`, case sensitivity control
+- **Example**: Categories, brands, status values
+
+### GEO Fields
+- **Purpose**: Geographic coordinates
+- **Format**: "latitude,longitude" (e.g., "37.7749,-122.4194")
+- **Features**: Geographic distance queries
+- **Options**: `STORED`
+
+### DATE Fields
+- **Purpose**: Timestamp and date data
+- **Format**: Unix timestamp in milliseconds
+- **Features**: Range queries, temporal filtering
+- **Options**: `STORED`, `INDEXED`, `FAST`
+
+## Search Query Syntax
+
+### Basic Queries
+```bash
+# Single term
+FT.SEARCH products "wireless"
+
+# Multiple terms (AND by default)
+FT.SEARCH products "wireless headphones"
+
+# Phrase query
+FT.SEARCH products "\"noise cancellation\""
+```
+
+### Field-Specific Queries
+```bash
+# Search in specific field
+FT.SEARCH products "title:wireless"
+
+# Multiple field queries
+FT.SEARCH products "title:wireless AND description:bluetooth"
+```
+
+### Boolean Operators
+```bash
+# AND operator
+FT.SEARCH products "wireless AND headphones"
+
+# OR operator  
+FT.SEARCH products "wireless OR bluetooth"
+
+# NOT operator
+FT.SEARCH products "headphones NOT wired"
+```
+
+### Wildcards and Fuzzy Search
+```bash
+# Wildcard search
+FT.SEARCH products "head*"
+
+# Fuzzy search (approximate matching)
+FT.SEARCH products "%headphone%"
+```
+
+### Range Queries
+```bash
+# Numeric range in query
+FT.SEARCH products "@price:[100 300]"
+
+# Date range
+FT.SEARCH products "@created_date:[1640995200000 1672531200000]"
+```
+
+## Filtering and Sorting
+
+### FILTER Clause
+```bash
+# Numeric filter
+FT.SEARCH products "headphones" FILTER price 100 300
+
+# Multiple filters
+FT.SEARCH products "*" FILTER price 100 500 FILTER rating 4 5
+```
+
+### LIMIT Clause
+```bash
+# Pagination
+FT.SEARCH products "wireless" LIMIT 0 10    # First 10 results
+FT.SEARCH products "wireless" LIMIT 10 10   # Next 10 results
+```
+
+### RETURN Clause
+```bash
+# Return specific fields
+FT.SEARCH products "*" RETURN title price
+
+# Return all stored fields (default)
+FT.SEARCH products "*"
+```
+
+## Performance Considerations
+
+### Indexing Strategy
+- Only index fields you need to search on
+- Use `FAST` option for frequently filtered numeric fields
+- Consider storage vs. search performance trade-offs
+
+### Query Optimization
+- Use specific field queries when possible
+- Combine filters with text queries for better performance
+- Use pagination with LIMIT for large result sets
+
+### Memory Usage
+- Tantivy indexes are memory-mapped for performance
+- Index size depends on document count and field configuration
+- Monitor disk space for index storage
+
+## Integration with Redis Commands
+
+Search indexes work alongside regular Redis data:
+
+```bash
+# Store product data in Redis hash
+HSET product:1 title "Wireless Headphones" price "199.99"
+
+# Index the same data for search
+FT.ADD products product:1 FIELDS title "Wireless Headphones" price 199.99
+
+# Search returns document IDs that can be used with Redis commands
+FT.SEARCH products "wireless"
+# Returns: product:1
+
+# Retrieve full data using Redis
+HGETALL product:1
+```
+
+## Example Use Cases
+
+### E-commerce Product Search
+```bash
+# Create product catalog index
+FT.CREATE catalog SCHEMA 
+  name TEXT STORED INDEXED TOKENIZED
+  description TEXT INDEXED TOKENIZED
+  price NUMERIC STORED INDEXED FAST
+  category TAG STORED
+  brand TAG STORED
+  rating NUMERIC STORED FAST
+
+# Add products
+FT.ADD catalog prod:1 FIELDS name "iPhone 14" price 999 category "phones" brand "apple" rating 4.5
+FT.ADD catalog prod:2 FIELDS name "Samsung Galaxy" price 899 category "phones" brand "samsung" rating 4.3
+
+# Search queries
+FT.SEARCH catalog "iPhone"
+FT.SEARCH catalog "phones" FILTER price 800 1000
+FT.SEARCH catalog "@brand:apple"
+```
+
+### Content Management
+```bash
+# Create content index
+FT.CREATE content SCHEMA
+  title TEXT STORED INDEXED TOKENIZED
+  body TEXT INDEXED TOKENIZED
+  author TAG STORED
+  published DATE STORED INDEXED
+  tags TAG STORED
+
+# Search content
+FT.SEARCH content "machine learning"
+FT.SEARCH content "@author:john AND @tags:ai"
+FT.SEARCH content "*" FILTER published 1640995200000 1672531200000
+```
+
+### Geographic Search
+```bash
+# Create location-based index
+FT.CREATE places SCHEMA
+  name TEXT STORED INDEXED TOKENIZED
+  location GEO STORED
+  type TAG STORED
+
+# Add locations
+FT.ADD places place:1 FIELDS name "Golden Gate Bridge" location "37.8199,-122.4783" type "landmark"
+
+# Geographic queries (future feature)
+FT.SEARCH places "@location:[37.7749 -122.4194 10 km]"
+```
+
+## Error Handling
+
+Common error responses:
+- `ERR index not found` - Index doesn't exist
+- `ERR field not found` - Field not defined in schema
+- `ERR invalid query syntax` - Malformed query
+- `ERR document not found` - Document ID doesn't exist
+
+## Best Practices
+
+1. **Schema Design**: Plan your schema carefully - changes require reindexing
+2. **Field Selection**: Only store and index fields you actually need
+3. **Batch Operations**: Add multiple documents efficiently
+4. **Query Testing**: Test queries for performance with realistic data
+5. **Monitoring**: Monitor index size and query performance
+6. **Backup**: Include search indexes in backup strategies
+
+## Future Enhancements
+
+Planned features:
+- Geographic distance queries
+- Advanced aggregations and faceting
+- Highlighting of search results
+- Synonyms and custom analyzers
+- Real-time suggestions and autocomplete
+- Index replication and sharding
--- a/examples/README.md
+++ b/examples/README.md
@@ -0,0 +1,171 @@
+# HeroDB Tantivy Search Examples
+
+This directory contains examples demonstrating HeroDB's full-text search capabilities powered by Tantivy.
+
+## Tantivy Search Demo (Bash Script)
+
+### Overview
+The `tantivy_search_demo.sh` script provides a comprehensive demonstration of HeroDB's search functionality using Redis commands. It showcases various search scenarios including basic text search, filtering, sorting, geographic queries, and more.
+
+### Prerequisites
+1. **HeroDB Server**: The server must be running on port 6381
+2. **Redis CLI**: The `redis-cli` tool must be installed and available in your PATH
+
+### Running the Demo
+
+#### Step 1: Start HeroDB Server
+```bash
+# From the project root directory
+cargo run -- --port 6381
+```
+
+#### Step 2: Run the Demo (in a new terminal)
+```bash
+# From the project root directory
+./examples/tantivy_search_demo.sh
+```
+
+### What the Demo Covers
+
+The script demonstrates 15 different search scenarios:
+
+1. **Index Creation** - Creating a search index with various field types
+2. **Data Insertion** - Adding sample products to the index
+3. **Basic Text Search** - Simple keyword searches
+4. **Filtered Search** - Combining text search with category filters
+5. **Numeric Range Search** - Finding products within price ranges
+6. **Sorting Results** - Ordering results by different fields
+7. **Limited Results** - Pagination and result limiting
+8. **Complex Queries** - Multi-field searches with sorting
+9. **Geographic Search** - Location-based queries
+10. **Index Information** - Getting statistics about the search index
+11. **Search Comparison** - Tantivy vs simple pattern matching
+12. **Fuzzy Search** - Typo tolerance and approximate matching
+13. **Phrase Search** - Exact phrase matching
+14. **Boolean Queries** - AND, OR, NOT operators
+15. **Cleanup** - Removing test data
+
+### Sample Data
+
+The demo uses a product catalog with the following fields:
+- **title** (TEXT) - Product name with higher search weight
+- **description** (TEXT) - Detailed product description
+- **category** (TAG) - Comma-separated categories
+- **price** (NUMERIC) - Product price for range queries
+- **rating** (NUMERIC) - Customer rating for sorting
+- **location** (GEO) - Geographic coordinates for location searches
+
+### Key Redis Commands Demonstrated
+
+#### Index Management
+```bash
+# Create search index
+FT.CREATE product_catalog ON HASH PREFIX 1 product: SCHEMA title TEXT WEIGHT 2.0 SORTABLE description TEXT category TAG SEPARATOR , price NUMERIC SORTABLE rating NUMERIC SORTABLE location GEO
+
+# Get index information
+FT.INFO product_catalog
+
+# Drop index
+FT.DROPINDEX product_catalog
+```
+
+#### Search Queries
+```bash
+# Basic text search
+FT.SEARCH product_catalog wireless
+
+# Filtered search
+FT.SEARCH product_catalog 'organic @category:{food}'
+
+# Numeric range
+FT.SEARCH product_catalog '@price:[50 150]'
+
+# Sorted results
+FT.SEARCH product_catalog '@category:{electronics}' SORTBY price ASC
+
+# Geographic search
+FT.SEARCH product_catalog '@location:[37.7749 -122.4194 50 km]'
+
+# Boolean queries
+FT.SEARCH product_catalog 'wireless AND audio'
+FT.SEARCH product_catalog 'coffee OR tea'
+
+# Phrase search
+FT.SEARCH product_catalog '"noise canceling"'
+```
+
+### Interactive Features
+
+The demo script includes:
+- **Colored output** for better readability
+- **Pause between steps** to review results
+- **Error handling** with clear error messages
+- **Automatic cleanup** of test data
+- **Progress indicators** showing what each step demonstrates
+
+### Troubleshooting
+
+#### HeroDB Not Running
+```
+✗ HeroDB is not running on port 6381
+ℹ Please start HeroDB with: cargo run -- --port 6381
+```
+**Solution**: Start the HeroDB server in a separate terminal.
+
+#### Redis CLI Not Found
+```
+redis-cli: command not found
+```
+**Solution**: Install Redis tools or use an alternative Redis client.
+
+#### Connection Refused
+```
+Could not connect to Redis at localhost:6381: Connection refused
+```
+**Solution**: Ensure HeroDB is running and listening on the correct port.
+
+### Manual Testing
+
+You can also run individual commands manually:
+
+```bash
+# Connect to HeroDB
+redis-cli -h localhost -p 6381
+
+# Create a simple index
+FT.CREATE myindex ON HASH SCHEMA title TEXT description TEXT
+
+# Add a document
+HSET doc:1 title "Hello World" description "This is a test document"
+
+# Search
+FT.SEARCH myindex hello
+```
+
+### Performance Notes
+
+- **Indexing**: Documents are indexed in real-time as they're added
+- **Search Speed**: Full-text search is much faster than pattern matching on large datasets
+- **Memory Usage**: Tantivy indexes are memory-efficient and disk-backed
+- **Scalability**: Supports millions of documents with sub-second search times
+
+### Advanced Features
+
+The demo showcases advanced Tantivy features:
+- **Relevance Scoring** - Results ranked by relevance
+- **Fuzzy Matching** - Handles typos and approximate matches
+- **Field Weighting** - Title field has higher search weight
+- **Multi-field Search** - Search across multiple fields simultaneously
+- **Geographic Queries** - Distance-based location searches
+- **Numeric Ranges** - Efficient range queries on numeric fields
+- **Tag Filtering** - Fast categorical filtering
+
+### Next Steps
+
+After running the demo, explore:
+1. **Custom Schemas** - Define your own field types and configurations
+2. **Large Datasets** - Test with thousands or millions of documents
+3. **Real Applications** - Integrate search into your applications
+4. **Performance Tuning** - Optimize for your specific use case
+
+For more information, see the [search documentation](../herodb/docs/search.md).
--- a/herodb/examples/age_bash_demo.sh
+++ b/herodb/examples/age_bash_demo.sh
--- a/herodb/examples/age_persist_demo.rs
+++ b/herodb/examples/age_persist_demo.rs
--- a/examples/simple_demo.sh
+++ b/examples/simple_demo.sh
@@ -0,0 +1,186 @@
+#!/bin/bash
+
+# Simple HeroDB Demo - Basic Redis Commands
+# This script demonstrates basic Redis functionality that's currently implemented
+
+set -e  # Exit on any error
+
+# Configuration
+REDIS_HOST="localhost"
+REDIS_PORT="6381"
+REDIS_CLI="redis-cli -h $REDIS_HOST -p $REDIS_PORT"
+
+# Colors for output
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+BLUE='\033[0;34m'
+YELLOW='\033[1;33m'
+NC='\033[0m' # No Color
+
+# Function to print colored output
+print_header() {
+    echo -e "${BLUE}=== $1 ===${NC}"
+}
+
+print_success() {
+    echo -e "${GREEN}✓ $1${NC}"
+}
+
+print_info() {
+    echo -e "${YELLOW}ℹ $1${NC}"
+}
+
+print_error() {
+    echo -e "${RED}✗ $1${NC}"
+}
+
+# Function to check if HeroDB is running
+check_herodb() {
+    print_info "Checking if HeroDB is running on port $REDIS_PORT..."
+    if ! $REDIS_CLI ping > /dev/null 2>&1; then
+        print_error "HeroDB is not running on port $REDIS_PORT"
+        print_info "Please start HeroDB with: cargo run -- --port $REDIS_PORT"
+        exit 1
+    fi
+    print_success "HeroDB is running and responding"
+}
+
+# Function to execute Redis command with error handling
+execute_cmd() {
+    local cmd="$1"
+    local description="$2"
+    
+    echo -e "${YELLOW}Command:${NC} $cmd"
+    if result=$($REDIS_CLI $cmd 2>&1); then
+        echo -e "${GREEN}Result:${NC} $result"
+        return 0
+    else
+        print_error "Failed: $description"
+        echo "Error: $result"
+        return 1
+    fi
+}
+
+# Main demo function
+main() {
+    clear
+    print_header "HeroDB Basic Functionality Demo"
+    echo "This demo shows basic Redis commands that are currently implemented"
+    echo "HeroDB runs on port $REDIS_PORT (instead of Redis default 6379)"
+    echo
+
+    # Check if HeroDB is running
+    check_herodb
+    echo
+
+    print_header "Step 1: Basic Key-Value Operations"
+    
+    execute_cmd "SET greeting 'Hello HeroDB!'" "Setting a simple key-value pair"
+    echo
+    execute_cmd "GET greeting" "Getting the value"
+    echo
+    execute_cmd "SET counter 42" "Setting a numeric value"
+    echo
+    execute_cmd "INCR counter" "Incrementing the counter"
+    echo
+    execute_cmd "GET counter" "Getting the incremented value"
+    echo
+
+    print_header "Step 2: Hash Operations"
+    
+    execute_cmd "HSET user:1 name 'John Doe' email 'john@example.com' age 30" "Setting hash fields"
+    echo
+    execute_cmd "HGET user:1 name" "Getting a specific field"
+    echo
+    execute_cmd "HGETALL user:1" "Getting all fields"
+    echo
+    execute_cmd "HLEN user:1" "Getting hash length"
+    echo
+
+    print_header "Step 3: List Operations"
+    
+    execute_cmd "LPUSH tasks 'Write code' 'Test code' 'Deploy code'" "Adding items to list"
+    echo
+    execute_cmd "LLEN tasks" "Getting list length"
+    echo
+    execute_cmd "LRANGE tasks 0 -1" "Getting all list items"
+    echo
+    execute_cmd "LPOP tasks" "Popping from left"
+    echo
+    execute_cmd "LRANGE tasks 0 -1" "Checking remaining items"
+    echo
+
+    print_header "Step 4: Key Management"
+    
+    execute_cmd "KEYS *" "Listing all keys"
+    echo
+    execute_cmd "EXISTS greeting" "Checking if key exists"
+    echo
+    execute_cmd "TYPE user:1" "Getting key type"
+    echo
+    execute_cmd "DBSIZE" "Getting database size"
+    echo
+
+    print_header "Step 5: Expiration"
+    
+    execute_cmd "SET temp_key 'temporary value'" "Setting temporary key"
+    echo
+    execute_cmd "EXPIRE temp_key 5" "Setting 5 second expiration"
+    echo
+    execute_cmd "TTL temp_key" "Checking time to live"
+    echo
+    print_info "Waiting 2 seconds..."
+    sleep 2
+    execute_cmd "TTL temp_key" "Checking TTL again"
+    echo
+
+    print_header "Step 6: Multiple Operations"
+    
+    execute_cmd "MSET key1 'value1' key2 'value2' key3 'value3'" "Setting multiple keys"
+    echo
+    execute_cmd "MGET key1 key2 key3" "Getting multiple values"
+    echo
+    execute_cmd "DEL key1 key2" "Deleting multiple keys"
+    echo
+    execute_cmd "EXISTS key1 key2 key3" "Checking existence of multiple keys"
+    echo
+
+    print_header "Step 7: Search Commands (Placeholder)"
+    print_info "Testing FT.CREATE command (currently returns placeholder response)"
+    
+    execute_cmd "FT.CREATE test_index SCHEMA title TEXT description TEXT" "Creating search index"
+    echo
+
+    print_header "Step 8: Server Information"
+    
+    execute_cmd "INFO" "Getting server information"
+    echo
+    execute_cmd "CONFIG GET dir" "Getting configuration"
+    echo
+
+    print_header "Step 9: Cleanup"
+    
+    execute_cmd "FLUSHDB" "Clearing database"
+    echo
+    execute_cmd "DBSIZE" "Confirming database is empty"
+    echo
+
+    print_header "Demo Summary"
+    echo "This demonstration showed:"
+    echo "• Basic key-value operations (GET, SET, INCR)"
+    echo "• Hash operations (HSET, HGET, HGETALL)"
+    echo "• List operations (LPUSH, LPOP, LRANGE)"
+    echo "• Key management (KEYS, EXISTS, TYPE, DEL)"
+    echo "• Expiration handling (EXPIRE, TTL)"
+    echo "• Multiple key operations (MSET, MGET)"
+    echo "• Server information commands"
+    echo
+    print_success "HeroDB basic functionality demo completed successfully!"
+    echo
+    print_info "Note: Full-text search (FT.*) commands are defined but not yet fully implemented"
+    print_info "To run HeroDB server: cargo run -- --port 6381"
+    print_info "To connect with redis-cli: redis-cli -h localhost -p 6381"
+}
+
+# Run the demo
+main "$@"
--- a/herodb/Cargo.toml
+++ b/herodb/Cargo.toml
@@ -1,29 +0,0 @@
-[package]
-name = "herodb"
-version = "0.0.1"
-authors = ["Pin Fang <fpfangpin@hotmail.com>"]
-edition = "2021"
-
-[dependencies]
-anyhow = "1.0.59"
-bytes = "1.3.0"
-thiserror = "1.0.32"
-tokio = { version = "1.23.0", features = ["full"] }
-clap = { version = "4.5.20", features = ["derive"] }
-byteorder = "1.4.3"
-futures = "0.3"
-sled = "0.34"
-redb = "2.1.3"
-serde = { version = "1.0", features = ["derive"] }
-serde_json = "1.0"
-bincode = "1.3"
-chacha20poly1305 = "0.10.1"
-rand = "0.8"
-sha2 = "0.10"
-age = "0.10"
-secrecy = "0.8"
-ed25519-dalek = "2"
-base64 = "0.22"
-
-[dev-dependencies]
-redis = { version = "0.24", features = ["aio", "tokio-comp"] }
--- a/herodb/run_tests.sh
+++ b/herodb/run_tests.sh
--- a/herodb/specs/backgroundinfo/encrypt.md
+++ b/herodb/specs/backgroundinfo/encrypt.md
--- a/specs/backgroundinfo/lance.md
+++ b/specs/backgroundinfo/lance.md
--- a/specs/backgroundinfo/lancedb.md
+++ b/specs/backgroundinfo/lancedb.md
--- a/herodb/specs/backgroundinfo/redb.md
+++ b/herodb/specs/backgroundinfo/redb.md
--- a/herodb/specs/backgroundinfo/redis_basic_client.md
+++ b/herodb/specs/backgroundinfo/redis_basic_client.md
--- a/herodb/specs/backgroundinfo/redis_basics.md
+++ b/herodb/specs/backgroundinfo/redis_basics.md
--- a/herodb/specs/backgroundinfo/redis_hset_functions.md
+++ b/herodb/specs/backgroundinfo/redis_hset_functions.md
--- a/herodb/specs/backgroundinfo/redis_lists.md
+++ b/herodb/specs/backgroundinfo/redis_lists.md
--- a/herodb/specs/backgroundinfo/sled.md
+++ b/herodb/specs/backgroundinfo/sled.md
--- a/herodb/specs/backgroundinfo/tantivy.md
+++ b/herodb/specs/backgroundinfo/tantivy.md
--- a/specs/lance_implementation.md
+++ b/specs/lance_implementation.md
@@ -0,0 +1,735 @@
+Looking at your request to ensure embedding happens with an external embedding provider configured in Redis at `config:core:aiembed:url`, I'll modify the implementation to use an external embedding service instead of local models.
+
+## Updated Implementation with External Embedding Provider
+
+### 1. Update Dependencies in `Cargo.toml`
+
+```toml
+[dependencies]
+# ... existing dependencies ...
+lance = "0.18"
+lance-index = "0.18"
+lance-linalg = "0.18"
+arrow = "52"
+arrow-array = "52"
+arrow-schema = "52"
+parquet = "52"
+uuid = { version = "1.10", features = ["v4"] }
+reqwest = { version = "0.11", features = ["json"] }
+serde = { version = "1.0", features = ["derive"] }
+serde_json = "1.0"
+base64 = "0.22"
+image = "0.25"
+```
+
+### 2. Create Enhanced Lance Module with External Embedding
+
+Create `src/lance_store.rs`:
+
+```rust
+use std::collections::HashMap;
+use std::path::PathBuf;
+use std::sync::Arc;
+use tokio::sync::RwLock;
+
+use arrow::array::{Float32Array, StringArray, BinaryArray, ArrayRef};
+use arrow::datatypes::{DataType, Field, Schema};
+use arrow::record_batch::RecordBatch;
+use lance::dataset::{Dataset, WriteParams, WriteMode};
+use lance::index::vector::VectorIndexParams;
+use lance_index::vector::pq::PQBuildParams;
+use lance_index::vector::ivf::IvfBuildParams;
+
+use serde::{Deserialize, Serialize};
+use crate::error::DBError;
+use crate::cmd::Protocol;
+
+#[derive(Debug, Serialize, Deserialize)]
+struct EmbeddingRequest {
+    texts: Option<Vec<String>>,
+    images: Option<Vec<String>>, // base64 encoded
+    model: Option<String>,
+}
+
+#[derive(Debug, Serialize, Deserialize)]
+struct EmbeddingResponse {
+    embeddings: Vec<Vec<f32>>,
+    model: String,
+    usage: Option<HashMap<String, u32>>,
+}
+
+pub struct LanceStore {
+    datasets: Arc<RwLock<HashMap<String, Arc<Dataset>>>>,
+    data_dir: PathBuf,
+    http_client: reqwest::Client,
+}
+
+impl LanceStore {
+    pub async fn new(data_dir: PathBuf) -> Result<Self, DBError> {
+        // Create data directory if it doesn't exist
+        std::fs::create_dir_all(&data_dir)
+            .map_err(|e| DBError(format!("Failed to create Lance data directory: {}", e)))?;
+        
+        let http_client = reqwest::Client::builder()
+            .timeout(std::time::Duration::from_secs(30))
+            .build()
+            .map_err(|e| DBError(format!("Failed to create HTTP client: {}", e)))?;
+        
+        Ok(Self {
+            datasets: Arc::new(RwLock::new(HashMap::new())),
+            data_dir,
+            http_client,
+        })
+    }
+    
+    /// Get embedding service URL from Redis config
+    async fn get_embedding_url(&self, server: &crate::server::Server) -> Result<String, DBError> {
+        // Get the embedding URL from Redis config
+        let key = "config:core:aiembed:url";
+        
+        // Use HGET to retrieve the URL from Redis hash
+        let cmd = crate::cmd::Cmd::HGet {
+            key: key.to_string(),
+            field: "url".to_string(),
+        };
+        
+        // Execute command to get the config
+        let result = cmd.run(server).await?;
+        
+        match result {
+            Protocol::BulkString(url) => Ok(url),
+            Protocol::SimpleString(url) => Ok(url),
+            Protocol::Nil => Err(DBError(
+                "Embedding service URL not configured. Set it with: HSET config:core:aiembed:url url <YOUR_EMBEDDING_SERVICE_URL>".to_string()
+            )),
+            _ => Err(DBError("Invalid embedding URL configuration".to_string())),
+        }
+    }
+    
+    /// Call external embedding service
+    async fn call_embedding_service(
+        &self,
+        server: &crate::server::Server,
+        texts: Option<Vec<String>>,
+        images: Option<Vec<String>>,
+    ) -> Result<Vec<Vec<f32>>, DBError> {
+        let url = self.get_embedding_url(server).await?;
+        
+        let request = EmbeddingRequest {
+            texts,
+            images,
+            model: None, // Let the service use its default
+        };
+        
+        let response = self.http_client
+            .post(&url)
+            .json(&request)
+            .send()
+            .await
+            .map_err(|e| DBError(format!("Failed to call embedding service: {}", e)))?;
+        
+        if !response.status().is_success() {
+            let status = response.status();
+            let error_text = response.text().await.unwrap_or_default();
+            return Err(DBError(format!(
+                "Embedding service returned error {}: {}", 
+                status, error_text
+            )));
+        }
+        
+        let embedding_response: EmbeddingResponse = response
+            .json()
+            .await
+            .map_err(|e| DBError(format!("Failed to parse embedding response: {}", e)))?;
+        
+        Ok(embedding_response.embeddings)
+    }
+    
+    pub async fn embed_text(
+        &self, 
+        server: &crate::server::Server,
+        texts: Vec<String>
+    ) -> Result<Vec<Vec<f32>>, DBError> {
+        if texts.is_empty() {
+            return Ok(Vec::new());
+        }
+        
+        self.call_embedding_service(server, Some(texts), None).await
+    }
+    
+    pub async fn embed_image(
+        &self,
+        server: &crate::server::Server,
+        image_bytes: Vec<u8>
+    ) -> Result<Vec<f32>, DBError> {
+        // Convert image bytes to base64
+        let base64_image = base64::encode(&image_bytes);
+        
+        let embeddings = self.call_embedding_service(
+            server, 
+            None, 
+            Some(vec![base64_image])
+        ).await?;
+        
+        embeddings.into_iter()
+            .next()
+            .ok_or_else(|| DBError("No embedding returned for image".to_string()))
+    }
+    
+    pub async fn create_dataset(
+        &self,
+        name: &str,
+        schema: Schema,
+    ) -> Result<(), DBError> {
+        let dataset_path = self.data_dir.join(format!("{}.lance", name));
+        
+        // Create empty dataset with schema
+        let write_params = WriteParams {
+            mode: WriteMode::Create,
+            ..Default::default()
+        };
+        
+        // Create an empty RecordBatch with the schema
+        let empty_batch = RecordBatch::new_empty(Arc::new(schema));
+        let batches = vec![empty_batch];
+        
+        let dataset = Dataset::write(
+            batches,
+            dataset_path.to_str().unwrap(),
+            Some(write_params)
+        ).await
+        .map_err(|e| DBError(format!("Failed to create dataset: {}", e)))?;
+        
+        let mut datasets = self.datasets.write().await;
+        datasets.insert(name.to_string(), Arc::new(dataset));
+        
+        Ok(())
+    }
+    
+    pub async fn write_vectors(
+        &self,
+        dataset_name: &str,
+        vectors: Vec<Vec<f32>>,
+        metadata: Option<HashMap<String, Vec<String>>>,
+    ) -> Result<usize, DBError> {
+        let dataset_path = self.data_dir.join(format!("{}.lance", dataset_name));
+        
+        // Open or get cached dataset
+        let dataset = self.get_or_open_dataset(dataset_name).await?;
+        
+        // Build RecordBatch
+        let num_vectors = vectors.len();
+        if num_vectors == 0 {
+            return Ok(0);
+        }
+        
+        let dim = vectors.first()
+            .ok_or_else(|| DBError("Empty vectors".to_string()))?
+            .len();
+        
+        // Flatten vectors
+        let flat_vectors: Vec<f32> = vectors.into_iter().flatten().collect();
+        let vector_array = Float32Array::from(flat_vectors);
+        let vector_array = arrow::array::FixedSizeListArray::try_new_from_values(
+            vector_array, 
+            dim as i32
+        ).map_err(|e| DBError(format!("Failed to create vector array: {}", e)))?;
+        
+        let mut arrays: Vec<ArrayRef> = vec![Arc::new(vector_array)];
+        let mut fields = vec![Field::new(
+            "vector",
+            DataType::FixedSizeList(
+                Arc::new(Field::new("item", DataType::Float32, true)),
+                dim as i32
+            ),
+            false
+        )];
+        
+        // Add metadata columns if provided
+        if let Some(metadata) = metadata {
+            for (key, values) in metadata {
+                if values.len() != num_vectors {
+                    return Err(DBError(format!(
+                        "Metadata field '{}' has {} values but expected {}", 
+                        key, values.len(), num_vectors
+                    )));
+                }
+                let array = StringArray::from(values);
+                arrays.push(Arc::new(array));
+                fields.push(Field::new(&key, DataType::Utf8, true));
+            }
+        }
+        
+        let schema = Arc::new(Schema::new(fields));
+        let batch = RecordBatch::try_new(schema, arrays)
+            .map_err(|e| DBError(format!("Failed to create RecordBatch: {}", e)))?;
+        
+        // Append to dataset
+        let write_params = WriteParams {
+            mode: WriteMode::Append,
+            ..Default::default()
+        };
+        
+        Dataset::write(
+            vec![batch],
+            dataset_path.to_str().unwrap(),
+            Some(write_params)
+        ).await
+        .map_err(|e| DBError(format!("Failed to write to dataset: {}", e)))?;
+        
+        // Refresh cached dataset
+        let mut datasets = self.datasets.write().await;
+        datasets.remove(dataset_name);
+        
+        Ok(num_vectors)
+    }
+    
+    pub async fn search_vectors(
+        &self,
+        dataset_name: &str,
+        query_vector: Vec<f32>,
+        k: usize,
+        nprobes: Option<usize>,
+        refine_factor: Option<usize>,
+    ) -> Result<Vec<(f32, HashMap<String, String>)>, DBError> {
+        let dataset = self.get_or_open_dataset(dataset_name).await?;
+        
+        // Build query
+        let mut query = dataset.scan();
+        query = query.nearest(
+            "vector",
+            &query_vector,
+            k,
+        ).map_err(|e| DBError(format!("Failed to build search query: {}", e)))?;
+        
+        if let Some(nprobes) = nprobes {
+            query = query.nprobes(nprobes);
+        }
+        
+        if let Some(refine) = refine_factor {
+            query = query.refine_factor(refine);
+        }
+        
+        // Execute search
+        let results = query
+            .try_into_stream()
+            .await
+            .map_err(|e| DBError(format!("Failed to execute search: {}", e)))?
+            .try_collect::<Vec<_>>()
+            .await
+            .map_err(|e| DBError(format!("Failed to collect results: {}", e)))?;
+        
+        // Process results
+        let mut output = Vec::new();
+        for batch in results {
+            // Get distances
+            let distances = batch
+                .column_by_name("_distance")
+                .ok_or_else(|| DBError("No distance column".to_string()))?
+                .as_any()
+                .downcast_ref::<Float32Array>()
+                .ok_or_else(|| DBError("Invalid distance type".to_string()))?;
+            
+            // Get metadata
+            for i in 0..batch.num_rows() {
+                let distance = distances.value(i);
+                let mut metadata = HashMap::new();
+                
+                for field in batch.schema().fields() {
+                    if field.name() != "vector" && field.name() != "_distance" {
+                        if let Some(col) = batch.column_by_name(field.name()) {
+                            if let Some(str_array) = col.as_any().downcast_ref::<StringArray>() {
+                                if !str_array.is_null(i) {
+                                    metadata.insert(
+                                        field.name().to_string(),
+                                        str_array.value(i).to_string()
+                                    );
+                                }
+                            }
+                        }
+                    }
+                }
+                
+                output.push((distance, metadata));
+            }
+        }
+        
+        Ok(output)
+    }
+    
+    pub async fn store_multimodal(
+        &self,
+        server: &crate::server::Server,
+        dataset_name: &str,
+        text: Option<String>,
+        image_bytes: Option<Vec<u8>>,
+        metadata: HashMap<String, String>,
+    ) -> Result<String, DBError> {
+        // Generate ID
+        let id = uuid::Uuid::new_v4().to_string();
+        
+        // Generate embeddings using external service
+        let embedding = if let Some(text) = text.as_ref() {
+            self.embed_text(server, vec![text.clone()]).await?
+                .into_iter()
+                .next()
+                .ok_or_else(|| DBError("No embedding returned".to_string()))?
+        } else if let Some(img) = image_bytes.as_ref() {
+            self.embed_image(server, img.clone()).await?
+        } else {
+            return Err(DBError("No text or image provided".to_string()));
+        };
+        
+        // Prepare metadata
+        let mut full_metadata = metadata;
+        full_metadata.insert("id".to_string(), id.clone());
+        if let Some(text) = text {
+            full_metadata.insert("text".to_string(), text);
+        }
+        if let Some(img) = image_bytes {
+            full_metadata.insert("image_base64".to_string(), base64::encode(img));
+        }
+        
+        // Convert metadata to column vectors
+        let mut metadata_cols = HashMap::new();
+        for (key, value) in full_metadata {
+            metadata_cols.insert(key, vec![value]);
+        }
+        
+        // Write to dataset
+        self.write_vectors(dataset_name, vec![embedding], Some(metadata_cols)).await?;
+        
+        Ok(id)
+    }
+    
+    pub async fn search_with_text(
+        &self,
+        server: &crate::server::Server,
+        dataset_name: &str,
+        query_text: String,
+        k: usize,
+        nprobes: Option<usize>,
+        refine_factor: Option<usize>,
+    ) -> Result<Vec<(f32, HashMap<String, String>)>, DBError> {
+        // Embed the query text using external service
+        let embeddings = self.embed_text(server, vec![query_text]).await?;
+        let query_vector = embeddings.into_iter()
+            .next()
+            .ok_or_else(|| DBError("No embedding returned for query".to_string()))?;
+        
+        // Search with the embedding
+        self.search_vectors(dataset_name, query_vector, k, nprobes, refine_factor).await
+    }
+    
+    pub async fn create_index(
+        &self,
+        dataset_name: &str,
+        index_type: &str,
+        num_partitions: Option<usize>,
+        num_sub_vectors: Option<usize>,
+    ) -> Result<(), DBError> {
+        let dataset = self.get_or_open_dataset(dataset_name).await?;
+        
+        let mut params = VectorIndexParams::default();
+        
+        match index_type.to_uppercase().as_str() {
+            "IVF_PQ" => {
+                params.ivf = IvfBuildParams {
+                    num_partitions: num_partitions.unwrap_or(256),
+                    ..Default::default()
+                };
+                params.pq = PQBuildParams {
+                    num_sub_vectors: num_sub_vectors.unwrap_or(16),
+                    ..Default::default()
+                };
+            }
+            _ => return Err(DBError(format!("Unsupported index type: {}", index_type))),
+        }
+        
+        dataset.create_index(
+            &["vector"],
+            lance::index::IndexType::Vector,
+            None,
+            &params,
+            true
+        ).await
+        .map_err(|e| DBError(format!("Failed to create index: {}", e)))?;
+        
+        Ok(())
+    }
+    
+    async fn get_or_open_dataset(&self, name: &str) -> Result<Arc<Dataset>, DBError> {
+        let mut datasets = self.datasets.write().await;
+        
+        if let Some(dataset) = datasets.get(name) {
+            return Ok(dataset.clone());
+        }
+        
+        let dataset_path = self.data_dir.join(format!("{}.lance", name));
+        if !dataset_path.exists() {
+            return Err(DBError(format!("Dataset '{}' does not exist", name)));
+        }
+        
+        let dataset = Dataset::open(dataset_path.to_str().unwrap())
+            .await
+            .map_err(|e| DBError(format!("Failed to open dataset: {}", e)))?;
+        
+        let dataset = Arc::new(dataset);
+        datasets.insert(name.to_string(), dataset.clone());
+        
+        Ok(dataset)
+    }
+    
+    pub async fn list_datasets(&self) -> Result<Vec<String>, DBError> {
+        let mut datasets = Vec::new();
+        
+        let entries = std::fs::read_dir(&self.data_dir)
+            .map_err(|e| DBError(format!("Failed to read data directory: {}", e)))?;
+        
+        for entry in entries {
+            let entry = entry.map_err(|e| DBError(format!("Failed to read entry: {}", e)))?;
+            let path = entry.path();
+            
+            if path.is_dir() {
+                if let Some(name) = path.file_name() {
+                    if let Some(name_str) = name.to_str() {
+                        if name_str.ends_with(".lance") {
+                            let dataset_name = name_str.trim_end_matches(".lance");
+                            datasets.push(dataset_name.to_string());
+                        }
+                    }
+                }
+            }
+        }
+        
+        Ok(datasets)
+    }
+    
+    pub async fn drop_dataset(&self, name: &str) -> Result<(), DBError> {
+        // Remove from cache
+        let mut datasets = self.datasets.write().await;
+        datasets.remove(name);
+        
+        // Delete from disk
+        let dataset_path = self.data_dir.join(format!("{}.lance", name));
+        if dataset_path.exists() {
+            std::fs::remove_dir_all(dataset_path)
+                .map_err(|e| DBError(format!("Failed to delete dataset: {}", e)))?;
+        }
+        
+        Ok(())
+    }
+    
+    pub async fn get_dataset_info(&self, name: &str) -> Result<HashMap<String, String>, DBError> {
+        let dataset = self.get_or_open_dataset(name).await?;
+        
+        let mut info = HashMap::new();
+        info.insert("name".to_string(), name.to_string());
+        info.insert("version".to_string(), dataset.version().to_string());
+        info.insert("num_rows".to_string(), dataset.count_rows().await?.to_string());
+        
+        // Get schema info
+        let schema = dataset.schema();
+        let fields: Vec<String> = schema.fields()
+            .iter()
+            .map(|f| format!("{}:{}", f.name(), f.data_type()))
+            .collect();
+        info.insert("schema".to_string(), fields.join(", "));
+        
+        Ok(info)
+    }
+}
+```
+
+### 3. Update Command Implementations
+
+Update the command implementations to pass the server reference for embedding service access:
+
+```rust
+// In cmd.rs, update the lance command implementations
+
+async fn lance_store_cmd(
+    server: &Server,
+    dataset: &str,
+    text: Option<String>,
+    image_base64: Option<String>,
+    metadata: HashMap<String, String>,
+) -> Result<Protocol, DBError> {
+    let lance_store = server.lance_store()?;
+    
+    // Decode image if provided
+    let image_bytes = if let Some(b64) = image_base64 {
+        Some(base64::decode(b64).map_err(|e| 
+            DBError(format!("Invalid base64 image: {}", e)))?)
+    } else {
+        None
+    };
+    
+    // Pass server reference for embedding service access
+    let id = lance_store.store_multimodal(
+        server,  // Pass server to access Redis config
+        dataset,
+        text,
+        image_bytes,
+        metadata,
+    ).await?;
+    
+    Ok(Protocol::BulkString(id))
+}
+
+async fn lance_embed_text_cmd(
+    server: &Server,
+    texts: &[String],
+) -> Result<Protocol, DBError> {
+    let lance_store = server.lance_store()?;
+    
+    // Pass server reference for embedding service access
+    let embeddings = lance_store.embed_text(server, texts.to_vec()).await?;
+    
+    // Return as array of vectors
+    let mut output = Vec::new();
+    for embedding in embeddings {
+        let vector_str = format!("[{}]", 
+            embedding.iter()
+                .map(|f| f.to_string())
+                .collect::<Vec<_>>()
+                .join(",")
+        );
+        output.push(Protocol::BulkString(vector_str));
+    }
+    
+    Ok(Protocol::Array(output))
+}
+
+async fn lance_search_text_cmd(
+    server: &Server,
+    dataset: &str,
+    query_text: &str,
+    k: usize,
+    nprobes: Option<usize>,
+    refine_factor: Option<usize>,
+) -> Result<Protocol, DBError> {
+    let lance_store = server.lance_store()?;
+    
+    // Search using text query (will be embedded automatically)
+    let results = lance_store.search_with_text(
+        server,
+        dataset,
+        query_text.to_string(),
+        k,
+        nprobes,
+        refine_factor,
+    ).await?;
+    
+    // Format results
+    let mut output = Vec::new();
+    for (distance, metadata) in results {
+        let metadata_json = serde_json::to_string(&metadata)
+            .unwrap_or_else(|_| "{}".to_string());
+        
+        output.push(Protocol::Array(vec![
+            Protocol::BulkString(distance.to_string()),
+            Protocol::BulkString(metadata_json),
+        ]));
+    }
+    
+    Ok(Protocol::Array(output))
+}
+
+// Add new command for text-based search
+pub enum Cmd {
+    // ... existing commands ...
+    LanceSearchText {
+        dataset: String,
+        query_text: String,
+        k: usize,
+        nprobes: Option<usize>,
+        refine_factor: Option<usize>,
+    },
+}
+```
+
+## Usage Examples
+
+### 1. Configure the Embedding Service
+
+First, users need to configure the embedding service URL:
+
+```bash
+# Configure the embedding service endpoint
+redis-cli> HSET config:core:aiembed:url url "http://localhost:8000/embeddings"
+OK
+
+# Or use a cloud service
+redis-cli> HSET config:core:aiembed:url url "https://api.openai.com/v1/embeddings"
+OK
+```
+
+### 2. Use Lance Commands with Automatic External Embedding
+
+```bash
+# Create a dataset
+redis-cli> LANCE.CREATE products DIM 1536 SCHEMA name:string price:float category:string
+OK
+
+# Store text with automatic embedding (calls external service)
+redis-cli> LANCE.STORE products TEXT "Wireless noise-canceling headphones with 30-hour battery" name:AirPods price:299.99 category:Electronics
+"uuid-123-456"
+
+# Search using text query (automatically embeds the query)
+redis-cli> LANCE.SEARCH.TEXT products "best headphones for travel" K 5
+1) "0.92" 
+2) "{\"id\":\"uuid-123\",\"name\":\"AirPods\",\"price\":\"299.99\"}"
+
+# Get embeddings directly
+redis-cli> LANCE.EMBED.TEXT "This text will be embedded"
+1) "[0.123, 0.456, 0.789, ...]"
+```
+
+## External Embedding Service API Specification
+
+The external embedding service should accept POST requests with this format:
+
+```json
+// Request
+{
+  "texts": ["text1", "text2"],  // Optional
+  "images": ["base64_img1"],    // Optional
+  "model": "text-embedding-ada-002"  // Optional
+}
+
+// Response
+{
+  "embeddings": [[0.1, 0.2, ...], [0.3, 0.4, ...]],
+  "model": "text-embedding-ada-002",
+  "usage": {
+    "prompt_tokens": 100,
+    "total_tokens": 100
+  }
+}
+```
+
+## Error Handling
+
+The implementation includes comprehensive error handling:
+
+1. **Missing Configuration**: Clear error message if embedding URL not configured
+2. **Service Failures**: Graceful handling of embedding service errors
+3. **Timeout Protection**: 30-second timeout for embedding requests
+4. **Retry Logic**: Could be added for resilience
+
+## Benefits of This Approach
+
+1. **Flexibility**: Supports any embedding service with compatible API
+2. **Cost Control**: Use your preferred embedding provider
+3. **Scalability**: Embedding service can be scaled independently
+4. **Consistency**: All embeddings use the same configured service
+5. **Security**: API keys and endpoints stored securely in Redis
+
+This implementation ensures that all embedding operations go through the external service configured in Redis, providing a clean separation between the vector database functionality and the embedding generation.
+
+
+TODO EXTRA:
+
+- secret for the embedding service API key
+
--- a/herodb/src/age.rs
+++ b/herodb/src/age.rs
--- a/herodb/src/cmd.rs
+++ b/herodb/src/cmd.rs
--- a/herodb/src/crypto.rs
+++ b/herodb/src/crypto.rs
--- a/herodb/src/error.rs
+++ b/herodb/src/error.rs
--- a/herodb/src/lib.rs
+++ b/herodb/src/lib.rs
--- a/herodb/src/main.rs
+++ b/herodb/src/main.rs
@@ -51,6 +51,7 @@ async fn main() {
    // new DB option
    let option = herodb::options::DBOption {
        dir: args.dir,
+        port,
        debug: args.debug,
        encryption_key: args.encryption_key,
        encrypt: args.encrypt,
--- a/herodb/src/options.rs
+++ b/herodb/src/options.rs
@@ -7,6 +7,7 @@ pub enum BackendType {
 #[derive(Debug, Clone)]
 pub struct DBOption {
    pub dir: String,
+    pub port: u16,
    pub debug: bool,
    pub encrypt: bool,
    pub encryption_key: Option<String>,
--- a/herodb/src/protocol.rs
+++ b/herodb/src/protocol.rs
--- a/herodb/src/server.rs
+++ b/herodb/src/server.rs
--- a/herodb/src/storage/mod.rs
+++ b/herodb/src/storage/mod.rs
--- a/herodb/src/storage/storage_basic.rs
+++ b/herodb/src/storage/storage_basic.rs
--- a/herodb/src/storage/storage_extra.rs
+++ b/herodb/src/storage/storage_extra.rs
--- a/herodb/src/storage/storage_hset.rs
+++ b/herodb/src/storage/storage_hset.rs
--- a/herodb/src/storage/storage_lists.rs
+++ b/herodb/src/storage/storage_lists.rs
--- a/herodb/src/storage_sled/mod.rs
+++ b/herodb/src/storage_sled/mod.rs
--- a/herodb/src/storage_trait.rs
+++ b/herodb/src/storage_trait.rs
--- a/herodb/test_herodb.sh
+++ b/herodb/test_herodb.sh
--- a/herodb/tests/debug_hset.rs
+++ b/herodb/tests/debug_hset.rs
@@ -27,6 +27,7 @@ async fn debug_hset_simple() {
        debug: false,
        encrypt: false,
        encryption_key: None,
+        backend: herodb::options::BackendType::Redb,
    };
    
    let mut server = Server::new(option).await;
--- a/herodb/tests/debug_hset_simple.rs
+++ b/herodb/tests/debug_hset_simple.rs
@@ -18,6 +18,7 @@ async fn debug_hset_return_value() {
        debug: false,
        encrypt: false,
        encryption_key: None,
+        backend: herodb::options::BackendType::Redb,
    };
    
    let mut server = Server::new(option).await;
--- a/herodb/tests/debug_protocol.rs
+++ b/herodb/tests/debug_protocol.rs
--- a/herodb/tests/redis_integration_tests.rs
+++ b/herodb/tests/redis_integration_tests.rs
--- a/herodb/tests/redis_tests.rs
+++ b/herodb/tests/redis_tests.rs
@@ -22,6 +22,7 @@ async fn start_test_server(test_name: &str) -> (Server, u16) {
        debug: true,
        encrypt: false,
        encryption_key: None,
+        backend: herodb::options::BackendType::Redb,
    };
    
    let server = Server::new(option).await;
--- a/herodb/tests/simple_integration_test.rs
+++ b/herodb/tests/simple_integration_test.rs
@@ -24,6 +24,7 @@ async fn start_test_server(test_name: &str) -> (Server, u16) {
        debug: true,
        encrypt: false,
        encryption_key: None,
+        backend: herodb::options::BackendType::Redb,
    };
    
    let server = Server::new(option).await;
--- a/herodb/tests/simple_redis_test.rs
+++ b/herodb/tests/simple_redis_test.rs
@@ -22,6 +22,7 @@ async fn start_test_server(test_name: &str) -> (Server, u16) {
        debug: false,
        encrypt: false,
        encryption_key: None,
+        backend: herodb::options::BackendType::Redb,
    };
    
    let server = Server::new(option).await;
--- a/herodb/tests/usage_suite.rs
+++ b/herodb/tests/usage_suite.rs
@@ -22,6 +22,7 @@ async fn start_test_server(test_name: &str) -> (Server, u16) {
        debug: false,
        encrypt: false,
        encryption_key: None,
+        backend: herodb::options::BackendType::Redb,
    };

    let server = Server::new(option).await;
@@ -500,11 +501,11 @@ async fn test_07_age_stateless_suite() {
    let mut s = connect(port).await;

    // GENENC -> [recipient, identity]
-    let gen = send_cmd(&mut s, &["AGE", "GENENC"]).await;
+    let genenc = send_cmd(&mut s, &["AGE", "GENENC"]).await;
    assert!(
-        gen.starts_with("*2\r\n$"),
+        genenc.starts_with("*2\r\n$"),
        "AGE GENENC should return array [recipient, identity], got:\n{}",
-        gen
+        genenc
    );

    // Parse simple RESP array of two bulk strings to extract keys
@@ -519,7 +520,7 @@ async fn test_07_age_stateless_suite() {
        let ident = lines.next().unwrap_or("").to_string();
        (recip, ident)
    }
-    let (recipient, identity) = parse_two_bulk_array(&gen);
+    let (recipient, identity) = parse_two_bulk_array(&genenc);
    assert!(
        recipient.starts_with("age1") && identity.starts_with("AGE-SECRET-KEY-1"),
        "Unexpected AGE key formats.\nrecipient: {}\nidentity: {}",
Author	SHA1	Message	Date
Maxime Van Hees	4bb24b38dd	fix typo in README	2025-09-11 15:34:03 +02:00
Maxime Van Hees	f3da14b957	Merge branch 'append'	2025-09-11 15:31:47 +02:00
Maxime Van Hees	5ea34b4445	update variable name as 'gen' is a reserved keyword since Rust 2024 edition	2025-09-11 15:25:26 +02:00
Maxime Van Hees	d9a3b711d1	Update tot Rust 2024 edition + update Cargo.toml file	2025-09-11 15:24:28 +02:00
Maxime Van Hees	d931770e90	Fix test suite + update Cargo.toml file	2025-09-09 16:04:31 +02:00
Timur Gordon	a87ec4dbb5	add readme	2025-08-27 15:39:59 +02:00
despiegk	a1127b72da	...	2025-08-23 05:20:42 +02:00
despiegk	3850df89be	...	2025-08-23 05:15:45 +02:00
despiegk	45195d403e	...	2025-08-23 05:12:17 +02:00
despiegk	f17b441ca1	...	2025-08-23 05:07:45 +02:00
despiegk	ff4ea1d844	...	2025-08-23 05:04:37 +02:00
despiegk	c9e1dcdb6c	...	2025-08-23 04:57:47 +02:00