Dev

.github/workflows/release.yml

@@ -0,0 +1,56 @@
+name: Release
+
+on:
+  push:
+    tags:
+      - 'v*'
+
+env:
+  CARGO_TERM_COLOR: always
+
+jobs:
+  # Publish Rust crate to crates.io
+  publish-crates:
+    name: Publish to crates.io
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: dtolnay/rust-toolchain@stable
+      - name: Publish vectorless crate
+        run: cargo publish -p vectorless
+        env:
+          CARGO_REGISTRY_TOKEN: ${{ secrets.CARGO_REGISTRY_TOKEN }}
+
+  # Publish Python package to PyPI
+  publish-pypi:
+    name: Publish to PyPI
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write  # Trusted Publishers
+    steps:
+      - uses: actions/checkout@v4
+      - uses: dtolnay/rust-toolchain@stable
+      - uses: pyo3/maturin-action@v1
+        with:
+          command: publish
+          args: --skip-existing
+          maturin-version: latest
+
+  # Create GitHub Release
+  github-release:
+    name: GitHub Release
+    runs-on: ubuntu-latest
+    needs: [publish-crates, publish-pypi]
+    permissions:
+      contents: write
+    steps:
+      - uses: actions/checkout@v4
+      - name: Extract version from tag
+        id: version
+        run: echo "VERSION=${GITHUB_REF#refs/tags/v}" >> $GITHUB_OUTPUT
+      - name: Create GitHub Release
+        uses: softprops/action-gh-release@v2
+        with:
+          tag_name: ${{ github.ref_name }}
+          name: Release ${{ steps.version.outputs.VERSION }}
+          generate_release_notes: true

Cargo.toml

@@ -3,7 +3,7 @@ members = ["rust", "python"]
 resolver = "2"
 
 [workspace.package]
-version = "0.1.27"
+version = "0.1.28"
 edition = "2024"
 authors = ["zTgx <beautifularea@gmail.com>"]
 license = "Apache-2.0"

README.md

@@ -33,7 +33,6 @@ from vectorless import Engine, IndexContext
 async def main():
     # Create engine — api_key and model are required
     engine = Engine(
-        workspace="./data",
         api_key="sk-...",
         model="gpt-4o",
     )
@@ -63,7 +62,6 @@ use vectorless::client::{EngineBuilder, IndexContext, QueryContext};
 #[tokio::main]
 async fn main() -> vectorless::Result<()> {
     let engine = EngineBuilder::new()
-        .with_workspace("./data")
         .with_key("sk-...")
         .with_model("gpt-4o")
         .build()
@@ -75,7 +73,7 @@ async fn main() -> vectorless::Result<()> {
 
     // Query
     let result = engine.query(
-        QueryContext::new("What is the total revenue?").with_doc_id(doc_id)
+        QueryContext::new("What is the total revenue?").with_doc_ids(vec![doc_id.to_string()])
     ).await?;
     println!("Answer: {}", result.content);
 

docs/blog/2026-04-12-welcome/index.mdx

@@ -29,7 +29,6 @@ from vectorless import Engine, IndexContext
 
 async def main():
     engine = Engine(
-        workspace="./data",
         api_key="sk-...",
         model="gpt-4o",
     )
@@ -53,7 +52,6 @@ use vectorless::{EngineBuilder, IndexContext, QueryContext};
 #[tokio::main]
 async fn main() -> vectorless::Result<()> {
     let engine = EngineBuilder::new()
-        .with_workspace("./data")
         .with_key("sk-...")
         .with_model("gpt-4o")
         .build()
@@ -63,7 +61,7 @@ async fn main() -> vectorless::Result<()> {
     let doc_id = result.doc_id().unwrap();
 
     let result = engine.query(
-        QueryContext::new("What is the total revenue?").with_doc_id(doc_id)
+        QueryContext::new("What is the total revenue?").with_doc_ids(vec![doc_id.to_string()])
     ).await?;
     println!("{}", result.content);
 

docs/docs/examples/batch-indexing.mdx

@@ -14,7 +14,6 @@ from vectorless import Engine, IndexContext, IndexOptions
 
 async def main():
     engine = Engine(
-        workspace="./workspace",
         api_key="sk-...",
         model="gpt-4o",
     )
@@ -53,7 +52,6 @@ use vectorless::client::{Engine, EngineBuilder, IndexContext};
 #[tokio::main]
 async fn main() -> vectorless::Result<()> {
     let engine = EngineBuilder::new()
-        .with_workspace("./workspace")
         .with_key("sk-...")
         .with_model("gpt-4o")
         .build()

docs/docs/examples/multi-document.mdx

@@ -12,12 +12,11 @@ Query across multiple indexed documents using the cross-document strategy with g
 import asyncio
 from vectorless import (
     Engine, IndexContext, QueryContext,
-    IndexOptions, StrategyPreference
+    IndexOptions,
 )
 
 async def main():
     engine = Engine(
-        workspace="./workspace",
         api_key="sk-...",
         model="gpt-4o",
     )
@@ -44,7 +43,6 @@ async def main():
     result = await engine.query(
         QueryContext("Compare quarterly revenue trends")
         .with_doc_ids(doc_ids)
-        .with_strategy(StrategyPreference.CROSS_DOCUMENT)
     )
 
     for item in result.items:
@@ -54,7 +52,6 @@ async def main():
     # Or query entire workspace
     result = await engine.query(
         QueryContext("What documents discuss risk factors?")
-        .with_workspace()
     )
 
     print(f"\nFound in {len(result.items)} document(s)")

docs/docs/examples/quick-query.mdx

@@ -10,12 +10,11 @@ This example demonstrates the basic index-and-query workflow with both Python an
 
 ```python
 import asyncio
-from vectorless import Engine, IndexContext, QueryContext, StrategyPreference
+from vectorless import Engine, IndexContext, QueryContext
 
 async def main():
     # 1. Create engine
     engine = Engine(
-        workspace="./data",
         api_key="sk-...",
         model="gpt-4o",
     )
@@ -28,16 +27,14 @@ async def main():
     # 3. Simple keyword query
     answer = await engine.query(
         QueryContext("revenue")
-        .with_doc_id(doc_id)
-        .with_strategy(StrategyPreference.KEYWORD)
+        .with_doc_ids([doc_id])
     )
     print(f"Keyword result: {answer.single().content[:200]}")
 
     # 4. Complex reasoning query
     answer = await engine.query(
         QueryContext("What are the main factors affecting performance?")
-        .with_doc_id(doc_id)
-        .with_strategy(StrategyPreference.HYBRID)
+        .with_doc_ids([doc_id])
     )
     print(f"Score: {answer.single().score:.2f}")
     print(f"Hybrid result: {answer.single().content[:200]}")
@@ -58,7 +55,6 @@ use vectorless::StrategyPreference;
 async fn main() -> vectorless::Result<()> {
     // 1. Create engine
     let engine = EngineBuilder::new()
-        .with_workspace("./data")
         .with_key("sk-...")
         .with_model("gpt-4o")
         .build()
@@ -72,7 +68,7 @@ async fn main() -> vectorless::Result<()> {
     // 3. Query with hybrid strategy
     let answer = engine.query(
         QueryContext::new("What are the main factors affecting performance?")
-            .with_doc_id(&doc_id)
+            .with_doc_ids(vec![doc_id.clone()])
     ).await?;
 
     if let Some(item) = answer.single() {

docs/docs/features/cross-document-graph.mdx

@@ -40,15 +40,13 @@ When using the cross-document strategy, the graph boosts scores for connected do
 4. Re-rank the merged result set
 
 ```python
-from vectorless import Engine, QueryContext, StrategyPreference
+from vectorless import Engine, QueryContext
 
-engine = Engine(workspace="./data", api_key="sk-...", model="gpt-4o")
+engine = Engine(api_key="sk-...", model="gpt-4o")
 
 # Query across all documents with graph boosting
 result = await engine.query(
-    QueryContext("Compare the approaches").with_strategy(
-        StrategyPreference.CROSS_DOCUMENT
-    )
+    QueryContext("Compare the approaches")
 )
 ```
 

docs/docs/features/pdf-support.mdx

@@ -11,15 +11,15 @@ Vectorless supports PDF documents with full page-level tracking and hierarchical
 ```python
 from vectorless import Engine, IndexContext
 
-engine = Engine(workspace="./data", api_key="sk-...", model="gpt-4o")
+engine = Engine(api_key="sk-...", model="gpt-4o")
 
 # Index a PDF
 result = await engine.index(IndexContext.from_path("./report.pdf"))
 doc_id = result.doc_id
 
 # Query the PDF
 answer = await engine.query(
-    QueryContext("What is discussed on page 5?").with_doc_id(doc_id)
+    QueryContext("What is discussed on page 5?").with_doc_ids([doc_id])
 )
 print(answer.single().content)
 ```

docs/docs/getting-started.mdx

@@ -26,7 +26,6 @@ from vectorless import Engine, IndexContext, QueryContext
 async def main():
     # Create an engine
     engine = Engine(
-        workspace="./data",
         api_key="sk-...",
         model="gpt-4o",
     )
@@ -38,7 +37,7 @@ async def main():
 
     # Query the document
     answer = await engine.query(
-        QueryContext("What is the total revenue?").with_doc_id(doc_id)
+        QueryContext("What is the total revenue?").with_doc_ids([doc_id])
     )
     print(answer.single().content)
 
@@ -49,7 +48,6 @@ asyncio.run(main())
 
 ```python
 engine = Engine(
-    workspace="./data",
     api_key="sk-...",
     model="gpt-4o",
     endpoint="https://api.your-provider.com/v1",
@@ -75,7 +73,6 @@ use vectorless::{EngineBuilder, IndexContext, QueryContext};
 #[tokio::main]
 async fn main() -> vectorless::Result<()> {
     let engine = EngineBuilder::new()
-        .with_workspace("./data")
         .with_key("sk-...")
         .with_model("gpt-4o")
         .build()
@@ -85,7 +82,7 @@ async fn main() -> vectorless::Result<()> {
     let doc_id = result.doc_id().unwrap();
 
     let result = engine.query(
-        QueryContext::new("What is the total revenue?").with_doc_id(doc_id)
+        QueryContext::new("What is the total revenue?").with_doc_ids(vec![doc_id.to_string()])
     ).await?;
 
     if let Some(item) = result.single() {

docs/docs/intro.mdx

@@ -28,7 +28,6 @@ from vectorless import Engine, IndexContext
 
 async def main():
     engine = Engine(
-        workspace="./data",
         api_key="sk-...",
         model="gpt-4o",
     )
@@ -55,7 +54,6 @@ use vectorless::{EngineBuilder, IndexContext, QueryContext};
 #[tokio::main]
 async fn main() -> vectorless::Result<()> {
     let engine = EngineBuilder::new()
-        .with_workspace("./data")
         .with_key("sk-...")
         .with_model("gpt-4o")
         .build()
@@ -65,7 +63,7 @@ async fn main() -> vectorless::Result<()> {
     let doc_id = result.doc_id().unwrap();
 
     let result = engine.query(
-        QueryContext::new("What is the total revenue?").with_doc_id(doc_id)
+        QueryContext::new("What is the total revenue?").with_doc_ids(vec![doc_id.to_string()])
     ).await?;
     println!("{}", result.content);
 

docs/docs/retrieval/search-algorithms.mdx

@@ -72,7 +72,7 @@ from vectorless import QueryContext
 
 ctx = (
     QueryContext("complex multi-hop question")
-    .with_doc_id(doc_id)
+    .with_doc_ids([doc_id])
     .with_depth_limit(10)      # Max tree traversal depth
     .with_max_tokens(4000)     # Max tokens in result
 )

docs/docs/retrieval/strategies.mdx

@@ -21,11 +21,9 @@ Vectorless provides five retrieval strategies, each designed for different query
 Fast TF-IDF/BM25 matching against the pre-computed reasoning index. No LLM calls during search.
 
 ```python
-from vectorless import QueryContext, StrategyPreference
+from vectorless import QueryContext
 
-ctx = QueryContext("revenue").with_doc_id(doc_id).with_strategy(
-    StrategyPreference.KEYWORD
-)
+ctx = QueryContext("revenue").with_doc_ids([doc_id])
 ```
 
 Use when:
@@ -38,9 +36,7 @@ Use when:
 LLM-powered tree navigation with full contextual understanding. The LLM sees the table of contents, node summaries, and makes navigation decisions at each level.
 
 ```python
-ctx = QueryContext("Explain the relationship between architecture and performance").with_doc_id(doc_id).with_strategy(
-    StrategyPreference.LLM
-)
+ctx = QueryContext("Explain the relationship between architecture and performance").with_doc_ids([doc_id])
 ```
 
 Use when:
@@ -53,9 +49,7 @@ Use when:
 Two-phase retrieval: BM25 pre-filter followed by LLM refinement. Combines the speed of keyword matching with the accuracy of LLM reasoning.
 
 ```python
-ctx = QueryContext("What are the growth trends?").with_doc_id(doc_id).with_strategy(
-    StrategyPreference.HYBRID
-)
+ctx = QueryContext("What are the growth trends?").with_doc_ids([doc_id])
 ```
 
 The recommended default for most queries. Fast pre-filtering reduces the number of nodes sent to the LLM, keeping token costs manageable while maintaining high accuracy.
@@ -65,16 +59,14 @@ The recommended default for most queries. Fast pre-filtering reduces the number
 Searches across multiple indexed documents and aggregates results. Uses the cross-document relationship graph for score boosting.
 
 ```python
-ctx = QueryContext("Compare the architectures").with_strategy(
-    StrategyPreference.CROSS_DOCUMENT
-)
+ctx = QueryContext("Compare the architectures")
 ```
 
 When a high-confidence result is found in one document, neighbor documents in the graph receive a score boost, surfacing related content across the workspace.
 
 ## Auto Selection
 
-When using `StrategyPreference.AUTO` (default), the engine analyzes query complexity and selects the appropriate strategy:
+By default, the engine analyzes query complexity and automatically selects the appropriate strategy:
 
 - Simple keyword queries → Keyword strategy
 - Complex reasoning queries → Hybrid strategy