@feltdb/core 0.4.11 → 0.4.13

package/dist/create/server-source/crates/feltdb/src/capabilities/vector.rs

@@ -0,0 +1,482 @@
+/// Vector Search Capability
+///
+/// A concrete implementation of FlowCapability that maintains a vector search index.
+/// This demonstrates the capability extension model with a different type of projection
+/// compared to search - showing that the same capability contract works for diverse use cases.
+use crate::capability::{
+    CapabilityAccessModel, CapabilityContext, CapabilityId, CapabilityMetadata,
+    CapabilityOperationResult, CapabilityQuery, CapabilityQueryResult, CapabilityRole,
+    FlowCapability,
+};
+use crate::{Operation, OperationType, Result};
+use serde::{Deserialize, Serialize};
+use serde_json::{json, Value};
+use std::collections::HashMap;
+
+/// Vector embedding representation
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct VectorDocument {
+    pub key: String,
+    pub text: String,
+    pub embedding: Vec<f32>,
+    pub metadata: Value,
+}
+
+/// Vector search result
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct VectorSearchResult {
+    pub key: String,
+    pub text: String,
+    pub distance: f32,
+    pub metadata: Value,
+}
+
+/// Embedding provider trait for pluggable embeddings
+pub trait EmbeddingProvider: Send + Sync {
+    /// Generate embedding for text
+    fn embed(&self, text: &str) -> Result<Vec<f32>>;
+}
+
+/// Simple embedding provider using random vectors (for demo)
+pub struct DemoEmbeddingProvider;
+
+impl EmbeddingProvider for DemoEmbeddingProvider {
+    fn embed(&self, text: &str) -> Result<Vec<f32>> {
+        // Simple hash-based deterministic embedding for testing
+        use std::collections::hash_map::DefaultHasher;
+        use std::hash::{Hash, Hasher};
+
+        let mut hasher = DefaultHasher::new();
+        text.hash(&mut hasher);
+        let seed = hasher.finish();
+
+        // Generate deterministic vector using seed
+        let mut embedding = Vec::new();
+        for i in 0..10 {
+            let val = (((seed ^ (i as u64 * 31)) % 1000) as f32 / 1000.0) * 2.0 - 1.0;
+            embedding.push(val);
+        }
+
+        Ok(embedding)
+    }
+}
+
+/// Vector search capability implementation
+pub struct VectorCapability {
+    capability_id: CapabilityId,
+    metadata: CapabilityMetadata,
+    /// In-memory vector store
+    documents: HashMap<String, VectorDocument>,
+    /// Embedding provider
+    embedding_provider: Box<dyn EmbeddingProvider>,
+}
+
+impl VectorCapability {
+    pub fn new(embedding_provider: Box<dyn EmbeddingProvider>) -> Self {
+        let capability_id = CapabilityId::new("vector".to_string());
+        let access_model = CapabilityAccessModel::new(
+            vec!["*".to_string()],
+            vec!["vector.index".to_string()],
+            vec!["embedding-api".to_string()],
+        );
+
+        let metadata = CapabilityMetadata::new(
+            capability_id.clone(),
+            "Vector Search".to_string(),
+            "Maintains a vector search index over documents".to_string(),
+            CapabilityRole::Projection,
+            access_model,
+        );
+
+        Self {
+            capability_id,
+            metadata,
+            documents: HashMap::new(),
+            embedding_provider,
+        }
+    }
+
+    /// Create a new vector capability with default embedding provider
+    pub fn with_default_provider() -> Self {
+        Self::new(Box::new(DemoEmbeddingProvider))
+    }
+
+    /// Add or update a document with embedding
+    fn index_document(&mut self, doc: &VectorDocument) -> Result<()> {
+        self.documents.insert(doc.key.clone(), doc.clone());
+        Ok(())
+    }
+
+    /// Remove a document from the vector index
+    fn remove_document(&mut self, key: &str) -> Result<()> {
+        self.documents.remove(key);
+        Ok(())
+    }
+
+    /// Calculate cosine similarity between two vectors
+    fn cosine_similarity(vec1: &[f32], vec2: &[f32]) -> f32 {
+        let mut dot_product = 0.0f32;
+        let mut norm1 = 0.0f32;
+        let mut norm2 = 0.0f32;
+
+        for i in 0..vec1.len().min(vec2.len()) {
+            dot_product += vec1[i] * vec2[i];
+            norm1 += vec1[i] * vec1[i];
+            norm2 += vec2[i] * vec2[i];
+        }
+
+        if norm1 == 0.0 || norm2 == 0.0 {
+            return 0.0;
+        }
+
+        dot_product / (norm1.sqrt() * norm2.sqrt())
+    }
+
+    /// Find similar vectors
+    fn find_similar(
+        &self,
+        query_embedding: &[f32],
+        top_k: usize,
+    ) -> Result<Vec<VectorSearchResult>> {
+        let mut results = Vec::new();
+
+        for (_key, doc) in &self.documents {
+            let similarity = Self::cosine_similarity(query_embedding, &doc.embedding);
+            // Convert similarity (0-1) to distance (0-2)
+            let distance = 2.0 - (similarity + 1.0);
+
+            results.push(VectorSearchResult {
+                key: doc.key.clone(),
+                text: doc.text.clone(),
+                distance,
+                metadata: doc.metadata.clone(),
+            });
+        }
+
+        // Sort by distance (ascending - smallest distance is best match)
+        results.sort_by(|a, b| a.distance.partial_cmp(&b.distance).unwrap());
+        results.truncate(top_k);
+
+        Ok(results)
+    }
+}
+
+impl FlowCapability for VectorCapability {
+    fn id(&self) -> CapabilityId {
+        self.capability_id.clone()
+    }
+
+    fn metadata(&self) -> CapabilityMetadata {
+        self.metadata.clone()
+    }
+
+    fn initialize(&mut self, _context: &CapabilityContext) -> Result<()> {
+        Ok(())
+    }
+
+    fn on_operation(
+        &mut self,
+        operation: &Operation,
+        _context: &CapabilityContext,
+    ) -> Result<CapabilityOperationResult> {
+        // Only index Insert and Update operations
+        match operation.op_type {
+            OperationType::Insert | OperationType::Update => {
+                if let Some(value) = &operation.value {
+                    let text = if value.is_string() {
+                        value.as_str().unwrap_or("").to_string()
+                    } else {
+                        value.to_string()
+                    };
+
+                    // Generate embedding via provider
+                    let embedding = self.embedding_provider.embed(&text)?;
+
+                    let doc = VectorDocument {
+                        key: operation.key.clone(),
+                        text,
+                        embedding,
+                        metadata: json!({
+                            "source_operation": operation.op_id,
+                            "timestamp": operation.timestamp_ms,
+                        }),
+                    };
+
+                    self.index_document(&doc)?;
+                    Ok(CapabilityOperationResult::with_derived_state(json!({
+                        "embedded": true,
+                        "key": operation.key.clone(),
+                    })))
+                } else {
+                    Ok(CapabilityOperationResult::success())
+                }
+            }
+            OperationType::Delete => {
+                self.remove_document(&operation.key)?;
+                Ok(CapabilityOperationResult::success())
+            }
+        }
+    }
+
+    fn query(
+        &self,
+        query: &CapabilityQuery,
+        _context: &CapabilityContext,
+    ) -> Result<CapabilityQueryResult> {
+        if query.query_type != "vectorFind" {
+            return Ok(CapabilityQueryResult::error(format!(
+                "Unknown query type: {}",
+                query.query_type
+            )));
+        }
+
+        let query_text = query
+            .params
+            .get("query")
+            .and_then(|v| v.as_str())
+            .unwrap_or("");
+
+        let top_k = query
+            .params
+            .get("topK")
+            .and_then(|v| v.as_u64())
+            .unwrap_or(5) as usize;
+
+        // Generate embedding for query
+        let query_embedding = self.embedding_provider.embed(query_text)?;
+
+        // Find similar documents
+        let results = self.find_similar(&query_embedding, top_k)?;
+        let result_values: Vec<Value> = results
+            .iter()
+            .map(|r| {
+                json!({
+                    "key": r.key,
+                    "text": r.text,
+                    "distance": r.distance,
+                    "metadata": r.metadata,
+                })
+            })
+            .collect();
+
+        Ok(CapabilityQueryResult::success(result_values))
+    }
+
+    fn rebuild(&mut self, operations: &[Operation], context: &CapabilityContext) -> Result<()> {
+        // Clear existing index
+        self.documents.clear();
+
+        // Replay all operations
+        for op in operations {
+            self.on_operation(op, context)?;
+        }
+
+        Ok(())
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_vector_capability_creation() {
+        let cap = VectorCapability::with_default_provider();
+        assert_eq!(cap.id().0, "vector");
+        assert!(cap.metadata().access_model.can_read("docs"));
+        assert!(cap.metadata().access_model.can_write("vector.index"));
+    }
+
+    #[test]
+    fn test_vector_capability_initialization() {
+        let mut cap = VectorCapability::with_default_provider();
+        let context = CapabilityContext {
+            capability_id: cap.id(),
+            instance_id: "test-instance".to_string(),
+            sequence: 0,
+            version: 1,
+        };
+
+        assert!(cap.initialize(&context).is_ok());
+    }
+
+    #[test]
+    fn test_vector_capability_embedding() {
+        let mut cap = VectorCapability::with_default_provider();
+        let context = CapabilityContext {
+            capability_id: cap.id(),
+            instance_id: "test-instance".to_string(),
+            sequence: 0,
+            version: 1,
+        };
+
+        cap.initialize(&context).unwrap();
+
+        let op = Operation::insert(
+            1,
+            "instance-1".to_string(),
+            1,
+            "docs:1".to_string(),
+            json!("Rust is a systems programming language"),
+            "Document".to_string(),
+            "docs".to_string(),
+        );
+
+        let result = cap.on_operation(&op, &context).unwrap();
+        assert!(result.success);
+        assert!(result.produced_derived_state);
+    }
+
+    #[test]
+    fn test_vector_capability_query() {
+        let mut cap = VectorCapability::with_default_provider();
+        let context = CapabilityContext {
+            capability_id: cap.id(),
+            instance_id: "test-instance".to_string(),
+            sequence: 0,
+            version: 1,
+        };
+
+        cap.initialize(&context).unwrap();
+
+        let op1 = Operation::insert(
+            1,
+            "instance-1".to_string(),
+            1,
+            "docs:1".to_string(),
+            json!("Rust programming language"),
+            "Document".to_string(),
+            "docs".to_string(),
+        );
+
+        let op2 = Operation::insert(
+            2,
+            "instance-1".to_string(),
+            2,
+            "docs:2".to_string(),
+            json!("Python data science tutorial"),
+            "Document".to_string(),
+            "docs".to_string(),
+        );
+
+        cap.on_operation(&op1, &context).unwrap();
+        cap.on_operation(&op2, &context).unwrap();
+
+        let query = CapabilityQuery {
+            query_type: "vectorFind".to_string(),
+            params: json!({
+                "query": "Rust systems",
+                "topK": 5
+            }),
+        };
+
+        let results = cap.query(&query, &context).unwrap();
+        assert!(results.success);
+        assert!(results.results.len() > 0);
+    }
+
+    #[test]
+    fn test_vector_capability_delete() {
+        let mut cap = VectorCapability::with_default_provider();
+        let context = CapabilityContext {
+            capability_id: cap.id(),
+            instance_id: "test-instance".to_string(),
+            sequence: 0,
+            version: 1,
+        };
+
+        cap.initialize(&context).unwrap();
+
+        // Insert a document
+        let op1 = Operation::insert(
+            1,
+            "instance-1".to_string(),
+            1,
+            "docs:1".to_string(),
+            json!("Test document"),
+            "Document".to_string(),
+            "docs".to_string(),
+        );
+        cap.on_operation(&op1, &context).unwrap();
+
+        // Verify it's indexed
+        let query = CapabilityQuery {
+            query_type: "vectorFind".to_string(),
+            params: json!({"query": "test", "topK": 10}),
+        };
+        let results = cap.query(&query, &context).unwrap();
+        assert_eq!(results.results.len(), 1);
+
+        // Delete it
+        let op2 = Operation::delete(
+            2,
+            "instance-1".to_string(),
+            2,
+            "docs:1".to_string(),
+            "Document".to_string(),
+            "docs".to_string(),
+        );
+        cap.on_operation(&op2, &context).unwrap();
+
+        // Verify it's gone
+        let results = cap.query(&query, &context).unwrap();
+        assert_eq!(results.results.len(), 0);
+    }
+
+    #[test]
+    fn test_vector_similarity() {
+        let vec1 = vec![1.0, 0.0, 0.0];
+        let vec2 = vec![1.0, 0.0, 0.0];
+        let vec3 = vec![0.0, 1.0, 0.0];
+
+        let sim1 = VectorCapability::cosine_similarity(&vec1, &vec2);
+        let sim2 = VectorCapability::cosine_similarity(&vec1, &vec3);
+
+        assert!((sim1 - 1.0).abs() < 0.001); // Same vector - similarity = 1
+        assert!((sim2 - 0.0).abs() < 0.001); // Orthogonal - similarity = 0
+    }
+
+    #[test]
+    fn test_vector_capability_rebuild() {
+        let mut cap = VectorCapability::with_default_provider();
+        let context = CapabilityContext {
+            capability_id: cap.id(),
+            instance_id: "test-instance".to_string(),
+            sequence: 0,
+            version: 1,
+        };
+
+        cap.initialize(&context).unwrap();
+
+        let ops = vec![
+            Operation::insert(
+                1,
+                "instance-1".to_string(),
+                1,
+                "docs:1".to_string(),
+                json!("Machine learning"),
+                "Document".to_string(),
+                "docs".to_string(),
+            ),
+            Operation::insert(
+                2,
+                "instance-1".to_string(),
+                2,
+                "docs:2".to_string(),
+                json!("Deep neural networks"),
+                "Document".to_string(),
+                "docs".to_string(),
+            ),
+        ];
+
+        cap.rebuild(&ops, &context).unwrap();
+
+        let query = CapabilityQuery {
+            query_type: "vectorFind".to_string(),
+            params: json!({"query": "learning", "topK": 5}),
+        };
+        let results = cap.query(&query, &context).unwrap();
+        assert!(results.success);
+        assert!(results.results.len() > 0);
+    }
+}