Updated docs

README.md

@@ -72,10 +72,11 @@ pip install cortexadb[docs,pdf]  # Optional: For PDF/Docx support
 <details>
 <summary><b>Technical Architecture & Benchmarks</b></summary>
 
-### Performance Benchmarks (v0.1.7)
-Measured on M2 Mac with 1,000 chunks of text.
+### Performance Benchmarks (v0.1.8)
 
-| Operation | v0.1.6 (Sync) | v0.1.7 (Batch) | Improvement |
+CortexaDB `v0.1.8` introduced a new batching architecture. Measured on an M2 Mac with 1,000 chunks of text:
+
+| Operation | v0.1.6 (Sync) | v0.1.8 (Batch) | Improvement |
 |-----------|---------------|----------------|-------------|
 | Ingestion | 12.4s         | **0.12s**      | **103x Faster** |
 | Memory Add| 15ms          | 1ms            | 15x Faster |
@@ -86,7 +87,7 @@ Measured on M2 Mac with 1,000 chunks of text.
 ---
 
 ## License & Status
-CortexaDB is currently in **Beta (v0.1.7)**. It is released under the **MIT** and **Apache-2.0** licenses.  
+CortexaDB is currently in **Beta (v0.1.8)**. It is released under the **MIT** and **Apache-2.0** licenses.  
 We are actively refining the API and welcome feedback!
 
 ---

docs/content/docs/api/python.mdx

@@ -72,57 +72,55 @@ report = db.last_replay_report
 
 ## Memory Operations
 
-### `.remember(text, embedding=None, metadata=None)`
+### `.add(text=None, vector=None, metadata=None, collection=None)`
 
 Stores a new memory entry. If an embedder is configured and no embedding is provided, the text is auto-embedded.
 
 **Parameters:**
 
 | Parameter | Type | Default | Description |
 |-----------|------|---------|-------------|
-| `text` | `str` | Required | Text content to store |
-| `embedding` | `list[float]?` | `None` | Pre-computed embedding vector |
+| `text` | `str?` | `None` | Text content to store |
+| `vector` | `list[float]?` | `None` | Pre-computed embedding vector |
 | `metadata` | `dict[str, str]?` | `None` | Key-value metadata pairs |
+| `collection` | `str?` | `"default"` | Target collection |
 
 **Returns:** `int` - The assigned memory ID
 
 **Example:**
 ```python
-mid = db.remember("User prefers dark mode")
-mid = db.remember("text", metadata={"source": "onboarding"})
-mid = db.remember("text", embedding=[0.1, 0.2, ...])
+mid = db.add("User prefers dark mode")
+mid = db.add("text", metadata={"source": "onboarding"})
+mid = db.add("text", vector=[0.1, 0.2, ...], collection="agent_a")
 ```
 
 ---
 
-### `.ask(query, embedding=None, top_k=5, use_graph=False, recency_bias=False)`
+### `.query(text=None, vector=None)`
 
-Performs a hybrid search across the database.
+Starts a fluent query builder to search across the database.
 
-**Parameters:**
-
-| Parameter | Type | Default | Description |
-|-----------|------|---------|-------------|
-| `query` | `str` | Required | Search query text |
-| `embedding` | `list[float]?` | `None` | Pre-computed query embedding |
-| `top_k` | `int` | `5` | Number of results to return |
-| `use_graph` | `bool` | `False` | Enable graph expansion via BFS |
-| `recency_bias` | `bool` | `False` | Boost recent memories in scoring |
+**Methods:**
 
-**Returns:** `list[Hit]`
+| Method | Description |
+|--------|-------------|
+| `.limit(n)` | Set maximum number of results (default 5) |
+| `.collection(name)` | Filter to a specific collection |
+| `.use_graph()` | Enable hybrid graph traversal |
+| `.recency_bias()` | Boost recent memories in scoring |
+| `.execute()` | Run the query and return `list[Hit]` |
 
 **Example:**
 ```python
-hits = db.ask("What does the user prefer?")
-hits = db.ask("query", top_k=10, use_graph=True, recency_bias=True)
+hits = db.query("What does the user prefer?").limit(5).use_graph().execute()
 
 for hit in hits:
     print(f"ID: {hit.id}, Score: {hit.score:.3f}")
 ```
 
 ---
 
-### `.get_memory(mid)`
+### `.get(mid)`
 
 Retrieves a full memory entry by ID.
 
@@ -138,7 +136,7 @@ Retrieves a full memory entry by ID.
 
 **Example:**
 ```python
-mem = db.get_memory(42)
+mem = db.get(42)
 print(mem.id)          # 42
 print(mem.content)     # b"User prefers dark mode"
 print(mem.namespace)   # "default"
@@ -150,7 +148,7 @@ print(mem.embedding)   # [0.1, 0.2, ...] or None
 
 ---
 
-### `.delete_memory(mid)`
+### `.delete(mid)`
 
 Permanently deletes a memory and updates all indexes.
 
@@ -164,7 +162,7 @@ Permanently deletes a memory and updates all indexes.
 
 **Example:**
 ```python
-db.delete_memory(42)
+db.delete(42)
 ```
 
 ---
@@ -189,7 +187,7 @@ db.connect(1, 2, "relates_to")
 db.connect(1, 3, "caused_by")
 ```
 
-> Both memories must be in the same namespace. Cross-namespace edges are forbidden.
+> Both memories must be in the same collection. Cross-collection edges are forbidden.
 
 ---
 
@@ -229,7 +227,7 @@ Chunks text and stores each chunk as a memory.
 | `chunk_size` | `int` | `512` | Target chunk size in characters |
 | `overlap` | `int` | `50` | Overlap between chunks |
 | `metadata` | `dict?` | `None` | Metadata to attach to all chunks |
-| `namespace` | `str?` | `None` | Target namespace |
+| `collection` | `str?` | `None` | Target collection |
 
 **Returns:** `list[int]` - Memory IDs of stored chunks
 
@@ -248,7 +246,7 @@ Loads a file, chunks it, and stores each chunk.
 | `chunk_size` | `int` | `512` | Target chunk size |
 | `overlap` | `int` | `50` | Overlap between chunks |
 | `metadata` | `dict?` | `None` | Metadata for all chunks |
-| `namespace` | `str?` | `None` | Target namespace |
+| `collection` | `str?` | `None` | Target collection |
 
 **Supported formats:** `.txt`, `.md`, `.json`, `.docx` (requires `cortexadb[docs]`), `.pdf` (requires `cortexadb[pdf]`)
 
@@ -260,34 +258,28 @@ db.load("paper.pdf", strategy="recursive", chunk_size=1024)
 
 ---
 
-### `.ingest_document(text, chunk_size=512, overlap=50, metadata=None, namespace=None)`
-
-Legacy method for chunking and storing text. Uses fixed chunking.
-
----
-
-## Namespace
+## Collections
 
-### `.namespace(name, readonly=False)`
+### `.collection(name, readonly=False)`
 
-Returns a scoped view of the database for a specific namespace.
+Returns a scoped view of the database for a specific collection.
 
 **Parameters:**
 
 | Parameter | Type | Default | Description |
 |-----------|------|---------|-------------|
-| `name` | `str` | Required | Namespace name |
+| `name` | `str` | Required | Collection name |
 | `readonly` | `bool` | `False` | If `True`, write operations raise errors |
 
-**Returns:** `Namespace`
+**Returns:** `Collection`
 
 **Example:**
 ```python
-ns = db.namespace("agent_a")
-mid = ns.remember("text")
-hits = ns.ask("query")
-ns.delete_memory(mid)
-ns.ingest_document("long text")
+col = db.collection("agent_a")
+mid = col.add("text")
+hits = col.query("query").execute()
+col.delete(mid)
+col.ingest("long text")
 ```
 
 ---
@@ -382,12 +374,12 @@ Query result from `.ask()`.
 
 ### `Memory`
 
-Full memory entry from `.get_memory()`.
+Full memory entry from `.get()`.
 
 | Field | Type | Description |
 |-------|------|-------------|
 | `id` | `int` | Memory ID |
-| `namespace` | `str` | Namespace name |
+| `namespace` | `str` | Collection name (internal key) |
 | `content` | `bytes` | Raw content |
 | `embedding` | `list[float]?` | Vector embedding |
 | `metadata` | `dict[str, str]` | Key-value metadata |

docs/content/docs/api/rust.mdx

@@ -12,13 +12,15 @@ The high-level API for interacting with the database.
 ### Opening a Database
 
 ```rust
-use cortexadb_core::CortexaDB;
+use cortexadb_core::{CortexaDB, CortexaDBBuilder};
 
 // Simple open with default config
-let db = CortexaDB::open("/path/to/db", 128)?;
+let db = CortexaDBBuilder::new("/path/to/db", 128).build()?;
 
 // Builder pattern for advanced config
-let db = CortexaDB::builder("/path/to/db", config).build()?;
+let db = CortexaDBBuilder::new("/path/to/db", 128)
+    .with_sync_policy(cortexadb_core::engine::SyncPolicy::Async { interval_ms: 1000 })
+    .build()?;
 ```
 
 ---
@@ -142,6 +144,25 @@ println!("Indexed: {}", stats.indexed_embeddings);
 
 ---
 
+## Observability / Telemetry
+
+CortexaDB uses the standard Rust [`log`](https://crates.io/crates/log) crate for all internal diagnostics and telemetry. It issues structured `debug!` and `trace!` logs instead of printing to stdout/stderr.
+
+To see CortexaDB metrics and internal operations in your application, initialize a logger (like `env_logger` or `tracing-subscriber`):
+
+```rust
+use env_logger;
+
+fn main() {
+    // Initialize the logger before opening the database
+    env_logger::init();
+
+    // In your terminal, run with: RUST_LOG=cortexadb_core=debug cargo run
+}
+```
+
+---
+
 ## Types
 
 ### `Hit`

docs/content/docs/getting-started/quickstart.mdx

@@ -30,23 +30,23 @@ db = CortexaDB.open("agent.mem", dimension=128)
 
 ```python
 # Auto-embedding (requires embedder)
-mid1 = db.remember("The user prefers dark mode.")
-mid2 = db.remember("User works at Stripe.")
+mid1 = db.add("The user prefers dark mode.")
+mid2 = db.add("User works at Stripe.")
 
 # With metadata
-mid3 = db.remember("User's name is Alice.", metadata={"source": "onboarding"})
+mid3 = db.add("User's name is Alice.", metadata={"source": "onboarding"})
 ```
 
 ### 4. Query Memories
 
 ```python
 # Semantic search
-hits = db.ask("What does the user like?")
+hits = db.query("What does the user like?").execute()
 for hit in hits:
     print(f"ID: {hit.id}, Score: {hit.score:.3f}")
 
 # Retrieve full memory
-mem = db.get_memory(hits[0].id)
+mem = db.get(hits[0].id)
 print(mem.content)  # b"The user prefers dark mode."
 ```
 
@@ -68,12 +68,12 @@ db.load("document.pdf", strategy="recursive")
 db.ingest("Long article text here...", strategy="markdown")
 ```
 
-### 7. Use Namespaces
+### 7. Use Collections
 
 ```python
-agent_a = db.namespace("agent_a")
-agent_a.remember("Agent A's private memory")
-hits = agent_a.ask("query only agent A's memories")
+agent_a = db.collection("agent_a")
+agent_a.add("Agent A's private memory")
+hits = agent_a.query("query only agent A's memories").execute()
 ```
 
 ---
@@ -90,10 +90,10 @@ cortexadb-core = { git = "https://github.com/anaslimem/CortexaDB.git" }
 ### 2. Basic Usage
 
 ```rust
-use cortexadb_core::CortexaDB;
+use cortexadb_core::{CortexaDB, CortexaDBBuilder};
 
 fn main() -> Result<(), Box<dyn std::error::Error>> {
-    let db = CortexaDB::open("/tmp/agent.mem", 128)?;
+    let db = CortexaDBBuilder::new("/tmp/agent.mem", 128).build()?;
 
     // Store a memory with an embedding
     let embedding = vec![0.1; 128];