haiku.rag 0.6.0__tar.gz → 0.7.1__tar.gz

{haiku_rag-0.6.0 → haiku_rag-0.7.1}/.pre-commit-config.yaml

@@ -21,12 +21,12 @@ repos:
     hooks:
       - id: pyright
 
-  - repo: https://github.com/RodrigoGonzalez/check-mkdocs
-    rev: v1.2.0
-    hooks:
-      - id: check-mkdocs
-        name: check-mkdocs
-        args: ["--config", "mkdocs.yml"] # Optional, mkdocs.yml is the default
-        # If you have additional plugins or libraries that are not included in
-        # check-mkdocs, add them here
-        additional_dependencies: ["mkdocs-material"]
+  # - repo: https://github.com/RodrigoGonzalez/check-mkdocs
+  #   rev: v1.2.0
+  #   hooks:
+  #     - id: check-mkdocs
+  #       name: check-mkdocs
+  #       args: ["--config", "mkdocs.yml"] # Optional, mkdocs.yml is the default
+  #       # If you have additional plugins or libraries that are not included in
+  #       # check-mkdocs, add them here
+  #       additional_dependencies: ["mkdocs-material"]

haiku_rag-0.7.1/.python-version

@@ -0,0 +1 @@
+3.12

{haiku_rag-0.6.0 → haiku_rag-0.7.1}/PKG-INFO

@@ -1,11 +1,11 @@
 Metadata-Version: 2.4
 Name: haiku.rag
-Version: 0.6.0
-Summary: Retrieval Augmented Generation (RAG) with SQLite
+Version: 0.7.1
+Summary: Retrieval Augmented Generation (RAG) with LanceDB
 Author-email: Yiorgis Gozadinos <ggozadinos@gmail.com>
 License: MIT
 License-File: LICENSE
-Keywords: RAG,mcp,ml,sqlite,sqlite-vec
+Keywords: RAG,lancedb,mcp,ml,vector-database
 Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers
@@ -17,18 +17,18 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Typing :: Typed
-Requires-Python: >=3.11
-Requires-Dist: docling>=2.15.0
+Requires-Python: >=3.12
+Requires-Dist: docling>=2.49.0
 Requires-Dist: fastmcp>=2.8.1
 Requires-Dist: httpx>=0.28.1
+Requires-Dist: lancedb>=0.24.3
 Requires-Dist: ollama>=0.5.3
-Requires-Dist: pydantic-ai>=0.7.2
+Requires-Dist: pydantic-ai>=0.8.1
 Requires-Dist: pydantic>=2.11.7
 Requires-Dist: python-dotenv>=1.1.0
-Requires-Dist: rich>=14.0.0
-Requires-Dist: sqlite-vec>=0.1.6
-Requires-Dist: tiktoken>=0.9.0
-Requires-Dist: typer>=0.16.0
+Requires-Dist: rich>=14.1.0
+Requires-Dist: tiktoken>=0.11.0
+Requires-Dist: typer>=0.16.1
 Requires-Dist: watchfiles>=1.1.0
 Provides-Extra: mxbai
 Requires-Dist: mxbai-rerank>=0.1.6; extra == 'mxbai'
@@ -36,18 +36,20 @@ Provides-Extra: voyageai
 Requires-Dist: voyageai>=0.3.2; extra == 'voyageai'
 Description-Content-Type: text/markdown
 
-# Haiku SQLite RAG
+# Haiku RAG
 
-Retrieval-Augmented Generation (RAG) library on SQLite.
+Retrieval-Augmented Generation (RAG) library built on LanceDB.
 
-`haiku.rag` is a Retrieval-Augmented Generation (RAG) library built to work on SQLite alone without the need for external vector databases. It uses [sqlite-vec](https://github.com/asg017/sqlite-vec) for storing the embeddings and performs semantic (vector) search as well as full-text search combined through Reciprocal Rank Fusion. Both open-source (Ollama) as well as commercial (OpenAI, VoyageAI) embedding providers are supported.
+`haiku.rag` is a Retrieval-Augmented Generation (RAG) library built to work with LanceDB as a local vector database. It uses LanceDB for storing embeddings and performs semantic (vector) search as well as full-text search combined through native hybrid search with Reciprocal Rank Fusion. Both open-source (Ollama) as well as commercial (OpenAI, VoyageAI) embedding providers are supported.
+
+> **Note**: Starting with version 0.7.0, haiku.rag uses LanceDB instead of SQLite. If you have an existing SQLite database, use `haiku-rag migrate old_database.sqlite` to migrate your data safely.
 
 ## Features
 
-- **Local SQLite**: No external servers required
+- **Local LanceDB**: No external servers required, supports also LanceDB cloud storage, S3, Google Cloud & Azure
 - **Multiple embedding providers**: Ollama, VoyageAI, OpenAI
 - **Multiple QA providers**: Any provider/model supported by Pydantic AI
-- **Hybrid search**: Vector + full-text search with Reciprocal Rank Fusion
+- **Native hybrid search**: Vector + full-text search with native LanceDB RRF reranking
 - **Reranking**: Default search result reranking with MixedBread AI or Cohere
 - **Question answering**: Built-in QA agents on your documents
 - **File monitoring**: Auto-index files when run as server
@@ -77,6 +79,9 @@ haiku-rag ask "Who is the author of haiku.rag?" --cite
 # Rebuild database (re-chunk and re-embed all documents)
 haiku-rag rebuild
 
+# Migrate from SQLite to LanceDB
+haiku-rag migrate old_database.sqlite
+
 # Start server with file monitoring
 export MONITOR_DIRECTORIES="/path/to/docs"
 haiku-rag serve
@@ -87,7 +92,7 @@ haiku-rag serve
 ```python
 from haiku.rag.client import HaikuRAG
 
-async with HaikuRAG("database.db") as client:
+async with HaikuRAG("database.lancedb") as client:
     # Add document
     doc = await client.create_document("Your content")
 

{haiku_rag-0.6.0 → haiku_rag-0.7.1}/README.md

@@ -1,15 +1,17 @@
-# Haiku SQLite RAG
+# Haiku RAG
 
-Retrieval-Augmented Generation (RAG) library on SQLite.
+Retrieval-Augmented Generation (RAG) library built on LanceDB.
 
-`haiku.rag` is a Retrieval-Augmented Generation (RAG) library built to work on SQLite alone without the need for external vector databases. It uses [sqlite-vec](https://github.com/asg017/sqlite-vec) for storing the embeddings and performs semantic (vector) search as well as full-text search combined through Reciprocal Rank Fusion. Both open-source (Ollama) as well as commercial (OpenAI, VoyageAI) embedding providers are supported.
+`haiku.rag` is a Retrieval-Augmented Generation (RAG) library built to work with LanceDB as a local vector database. It uses LanceDB for storing embeddings and performs semantic (vector) search as well as full-text search combined through native hybrid search with Reciprocal Rank Fusion. Both open-source (Ollama) as well as commercial (OpenAI, VoyageAI) embedding providers are supported.
+
+> **Note**: Starting with version 0.7.0, haiku.rag uses LanceDB instead of SQLite. If you have an existing SQLite database, use `haiku-rag migrate old_database.sqlite` to migrate your data safely.
 
 ## Features
 
-- **Local SQLite**: No external servers required
+- **Local LanceDB**: No external servers required, supports also LanceDB cloud storage, S3, Google Cloud & Azure
 - **Multiple embedding providers**: Ollama, VoyageAI, OpenAI
 - **Multiple QA providers**: Any provider/model supported by Pydantic AI
-- **Hybrid search**: Vector + full-text search with Reciprocal Rank Fusion
+- **Native hybrid search**: Vector + full-text search with native LanceDB RRF reranking
 - **Reranking**: Default search result reranking with MixedBread AI or Cohere
 - **Question answering**: Built-in QA agents on your documents
 - **File monitoring**: Auto-index files when run as server
@@ -39,6 +41,9 @@ haiku-rag ask "Who is the author of haiku.rag?" --cite
 # Rebuild database (re-chunk and re-embed all documents)
 haiku-rag rebuild
 
+# Migrate from SQLite to LanceDB
+haiku-rag migrate old_database.sqlite
+
 # Start server with file monitoring
 export MONITOR_DIRECTORIES="/path/to/docs"
 haiku-rag serve
@@ -49,7 +54,7 @@ haiku-rag serve
 ```python
 from haiku.rag.client import HaikuRAG
 
-async with HaikuRAG("database.db") as client:
+async with HaikuRAG("database.lancedb") as client:
     # Add document
     doc = await client.create_document("Your content")
 

{haiku_rag-0.6.0 → haiku_rag-0.7.1}/docs/benchmarks.md

@@ -7,19 +7,19 @@ You can perform your own evaluations using as example the script found at
 
 ## Recall
 
-In order to calculate recall, we load the `News Stories` from `repliqa_3` which is 1035 documents and index them in a sqlite db. Subsequently, we run a search over the `question` field for each row of the dataset and check whether we match the document that answers the question.
+In order to calculate recall, we load the `News Stories` from `repliqa_3` (1035 documents) and index them. Subsequently, we run a search over the `question` field for each row of the dataset and check whether we match the document that answers the question. Questions for which the answer cannot be found in the documents are ignored.
 
 
-The recall obtained is ~0.73 for matching in the top result, raising to ~0.75 for the top 3 results.
+The recall obtained is ~0.79 for matching in the top result, raising to ~0.91 for the top 3 results with the "bare" default settings (Ollama `qwen3`, `mxbai-embed-large` embeddings, no reranking).
 
 | Embedding Model                       | Document in top 1 | Document in top 3 | Reranker               |
 |---------------------------------------|-------------------|-------------------|------------------------|
-| Ollama / `mxbai-embed-large`          | 0.77              | 0.89              | None                   |
-| Ollama / `mxbai-embed-large`          | 0.81              | 0.91              | `mxbai-rerank-base-v2` |
-| Ollama / `nomic-embed-text`           | 0.74              | 0.88              | None                   |
+| Ollama / `mxbai-embed-large`          | 0.79              | 0.91              | None                   |
+| Ollama / `mxbai-embed-large`          | 0.90              | 0.95              | `mxbai-rerank-base-v2` |
+<!-- | Ollama / `nomic-embed-text`           | 0.74              | 0.88              | None                   |
 | OpenAI / `text-embeddings-3-small`    | 0.75              | 0.88              | None                   |
 | OpenAI / `text-embeddings-3-small`    | 0.75              | 0.88              | None                   |
-| OpenAI / `text-embeddings-3-small`    | 0.83              | 0.90              | Cohere / `rerank-v3.5` |
+| OpenAI / `text-embeddings-3-small`    | 0.83              | 0.90              | Cohere / `rerank-v3.5` | -->
 
 ## Question/Answer evaluation
 
@@ -27,7 +27,10 @@ Again using the same dataset, we use a QA agent to answer the question. In addit
 
 | Embedding Model                    | QA Model                          | Accuracy  | Reranker               |
 |------------------------------------|-----------------------------------|-----------|------------------------|
-| Ollama / `mxbai-embed-large`       | Ollama / `qwen3`                  | 0.64      | None                   |
-| Ollama / `mxbai-embed-large`       | Ollama / `qwen3`                  | 0.72      | `mxbai-rerank-base-v2` |
-| Ollama / `mxbai-embed-large`       | Anthropic / `Claude Sonnet 3.7`   | 0.79      | None                   |
-| OpenAI / `text-embeddings-3-small` | OpenAI / `gpt-4-turbo`            | 0.62      | None                   |
+| Ollama / `mxbai-embed-large`       | Ollama / `qwen3`                  | 0.85      | None                   |
+| Ollama / `mxbai-embed-large`       | Ollama / `qwen3`                  | 0.87      | `mxbai-rerank-base-v2` |
+| Ollama / `mxbai-embed-large`       | Ollama / `qwen3:0.6b`             | 0.28      | None                   |
+
+Note the significant degradation when very small models are used such as `qwen3:0.6b`.
+<!-- | Ollama / `mxbai-embed-large`       | Anthropic / `Claude Sonnet 3.7`   | 0.79      | None                   |
+| OpenAI / `text-embeddings-3-small` | OpenAI / `gpt-4-turbo`            | 0.62      | None                   | -->

{haiku_rag-0.6.0 → haiku_rag-0.7.1}/docs/cli.md

@@ -45,6 +45,23 @@ haiku-rag rebuild
 
 Use this when you want to change things like the embedding model or chunk size for example.
 
+## Migration
+
+### Migrate from SQLite to LanceDB
+
+Migrate an existing SQLite database to LanceDB:
+
+```bash
+haiku-rag migrate /path/to/old_database.sqlite
+```
+
+This will:
+- Read all documents, chunks, embeddings, and settings from the SQLite database
+- Create a new LanceDB database with the same data in the same directory
+- Optimize the new database for best performance
+
+The original SQLite database remains unchanged, so you can safely migrate without risk of data loss.
+
 ## Search
 
 Basic search:
@@ -54,7 +71,7 @@ haiku-rag search "machine learning"
 
 With options:
 ```bash
-haiku-rag search "python programming" --limit 10 --k 100
+haiku-rag search "python programming" --limit 10
 ```
 
 ## Question Answering

{haiku_rag-0.6.0 → haiku_rag-0.7.1}/docs/configuration.md

@@ -109,25 +109,7 @@ See the [Pydantic AI documentation](https://ai.pydantic.dev/models/) for the com
 
 Reranking improves search quality by re-ordering the initial search results using specialized models. When enabled, the system retrieves more candidates (3x the requested limit) and then reranks them to return the most relevant results.
 
-Reranking is **automatically enabled** by default using Ollama, or if you install the appropriate reranking provider package.
-
-### Disabling Reranking
-
-To disable reranking completely for faster searches:
-
-```bash
-RERANK_PROVIDER=""
-```
-
-### Ollama (Default)
-
-Ollama reranking uses LLMs with structured output to rank documents by relevance:
-
-```bash
-RERANK_PROVIDER="ollama"
-RERANK_MODEL="qwen3:1.7b"  # or any model that supports structured output
-OLLAMA_BASE_URL="http://localhost:11434"
-```
+Reranking is **disabled by default** (`RERANK_PROVIDER=""`) for faster searches. You can enable it by configuring one of the providers below.
 
 ### MixedBread AI
 
@@ -158,11 +140,41 @@ COHERE_API_KEY="your-api-key"
 
 ### Database and Storage
 
+By default, `haiku.rag` uses a local LanceDB database:
+
 ```bash
-# Default data directory (where SQLite database is stored)
+# Default data directory (where local LanceDB is stored)
 DEFAULT_DATA_DIR="/path/to/data"
 ```
 
+For remote storage, use the `LANCEDB_URI` setting with various backends:
+
+```bash
+# LanceDB Cloud
+LANCEDB_URI="db://your-database-name"
+LANCEDB_API_KEY="your-api-key"
+LANCEDB_REGION="us-west-2"  # optional
+
+# Amazon S3
+LANCEDB_URI="s3://my-bucket/my-table"
+# Use AWS credentials or IAM roles
+
+# Azure Blob Storage
+LANCEDB_URI="az://my-container/my-table"
+# Use Azure credentials
+
+# Google Cloud Storage
+LANCEDB_URI="gs://my-bucket/my-table"
+# Use GCP credentials
+
+# HDFS
+LANCEDB_URI="hdfs://namenode:port/path/to/table"
+```
+
+Authentication is handled through standard cloud provider credentials (AWS CLI, Azure CLI, gcloud, etc.) or by setting `LANCEDB_API_KEY` for LanceDB Cloud.
+
+**Note:** Table optimization is automatically handled by LanceDB Cloud (`db://` URIs) and is disabled for better performance. For object storage backends (S3, Azure, GCS), optimization is still performed locally.
+
 ### Document Processing
 
 ```bash

{haiku_rag-0.6.0 → haiku_rag-0.7.1}/docs/index.md

@@ -1,12 +1,14 @@
 # haiku.rag
 
-`haiku.rag` is a Retrieval-Augmented Generation (RAG) library built to work on SQLite alone without the need for external vector databases. It uses [sqlite-vec](https://github.com/asg017/sqlite-vec) for storing the embeddings and performs semantic (vector) search as well as full-text search combined through Reciprocal Rank Fusion. Both open-source (Ollama, MixedBread AI) as well as commercial (OpenAI, VoyageAI) embedding providers are supported.
+`haiku.rag` is a Retrieval-Augmented Generation (RAG) library built to work with LanceDB as a local vector database. It uses LanceDB for storing embeddings and performs semantic (vector) search as well as full-text search combined through native hybrid search with Reciprocal Rank Fusion. Both open-source (Ollama, MixedBread AI) as well as commercial (OpenAI, VoyageAI) embedding providers are supported.
+
+> **Note**: Starting with version 0.7.0, haiku.rag uses LanceDB instead of SQLite. If you have an existing SQLite database, use `haiku-rag migrate old_database.sqlite` to migrate your data safely.
 
 ## Features
 
-- **Local SQLite**: No need to run additional servers
+- **Local LanceDB**: No need to run additional servers
 - **Support for various embedding providers**: Ollama, VoyageAI, OpenAI or add your own
-- **Hybrid Search**: Vector search using `sqlite-vec` combined with full-text search `FTS5`, using Reciprocal Rank Fusion
+- **Native Hybrid Search**: Vector search combined with full-text search using native LanceDB RRF reranking
 - **Reranking**: Optional result reranking with MixedBread AI or Cohere
 - **Question Answering**: Built-in QA agents using Ollama, OpenAI, or Anthropic.
 - **File monitoring**: Automatically index files when run as a server
@@ -26,7 +28,7 @@ Use from Python:
 ```python
 from haiku.rag.client import HaikuRAG
 
-async with HaikuRAG("database.db") as client:
+async with HaikuRAG("database.lancedb") as client:
     # Add a document
     doc = await client.create_document("Your content here")
 
@@ -34,7 +36,7 @@ async with HaikuRAG("database.db") as client:
     results = await client.search("query")
 
     # Ask questions
-    answer = await client.ask("Who is the author of haiku.rag?", rerank=False)
+    answer = await client.ask("Who is the author of haiku.rag?")
 ```
 
 Or use the CLI:
@@ -42,6 +44,7 @@ Or use the CLI:
 haiku-rag add "Your document content"
 haiku-rag search "query"
 haiku-rag ask "Who is the author of haiku.rag?"
+haiku-rag migrate old_database.sqlite  # Migrate from SQLite
 ```
 
 ## Documentation

{haiku_rag-0.6.0 → haiku_rag-0.7.1}/docs/installation.md

@@ -31,5 +31,4 @@ uv pip install haiku.rag[mxbai]
 ## Requirements
 
 - Python 3.10+
-- SQLite 3.38+
 - Ollama (for default embeddings)

{haiku_rag-0.6.0 → haiku_rag-0.7.1}/docs/mcp.md

@@ -19,10 +19,10 @@ The MCP server exposes `haiku.rag` as MCP tools for compatible MCP clients.
 
 ## Starting MCP Server
 
-The MCP server starts automatically with the serve command and supports `Streamable HTTP`, `stdio` and `SSE` transports:
+The MCP server starts automatically with the serve command and supports Streamable HTTP, stdio and SSE transports:
 
 ```bash
-# Default HTTP transport
+# Default streamable HTTP transport
 haiku-rag serve
 
 # stdio transport (for Claude Desktop)

{haiku_rag-0.6.0 → haiku_rag-0.7.1}/docs/python.md

@@ -9,7 +9,7 @@ from pathlib import Path
 from haiku.rag.client import HaikuRAG
 
 # Use as async context manager (recommended)
-async with HaikuRAG("path/to/database.db") as client:
+async with HaikuRAG("path/to/database.lancedb") as client:
     # Your code here
     pass
 ```
@@ -101,9 +101,9 @@ async for doc_id in client.rebuild_database():
 
 ## Searching Documents
 
-The search method performs hybrid search (vector + full-text) with **reranking enabled by default** for improved relevance:
+The search method performs native hybrid search (vector + full-text) using LanceDB with optional reranking for improved relevance:
 
-Basic search (with reranking):
+Basic hybrid search (default):
 ```python
 results = await client.search("machine learning algorithms", limit=5)
 for chunk, score in results:
@@ -112,13 +112,27 @@ for chunk, score in results:
     print(f"Document ID: {chunk.document_id}")
 ```
 
-With options:
+Search with different search types:
 ```python
+# Vector search only
 results = await client.search(
     query="machine learning",
-    limit=5,  # Maximum results to return
-    k=60,     # RRF parameter for reciprocal rank fusion
-    rerank=False  # Disable reranking for faster search
+    limit=5,
+    search_type="vector"
+)
+
+# Full-text search only
+results = await client.search(
+    query="machine learning",
+    limit=5,
+    search_type="fts"
+)
+
+# Hybrid search (default - combines vector + fts with native LanceDB RRF)
+results = await client.search(
+    query="machine learning",
+    limit=5,
+    search_type="hybrid"
 )
 
 # Process results

{haiku_rag-0.6.0 → haiku_rag-0.7.1}/docs/server.md

@@ -9,7 +9,7 @@ haiku-rag serve
 ```
 
 Transport options:
-- `--http` (default) - Streamable HTTP transport
+- Default - Streamable HTTP transport
 - `--stdio` - Standard input/output transport
 - `--sse` - Server-sent events transport
 

{haiku_rag-0.6.0 → haiku_rag-0.7.1}/mkdocs.yml

@@ -1,5 +1,5 @@
 site_name: haiku.rag
-site_description: Retrieval-Augmented Generation (RAG) library on SQLite.
+site_description: Retrieval-Augmented Generation (RAG) library on LanceDB.
 site_url: https://ggozad.github.io/haiku.rag/
 theme:
   name: material

{haiku_rag-0.6.0 → haiku_rag-0.7.1}/pyproject.toml

@@ -1,12 +1,12 @@
 [project]
 name = "haiku.rag"
-version = "0.6.0"
-description = "Retrieval Augmented Generation (RAG) with SQLite"
+version = "0.7.1"
+description = "Retrieval Augmented Generation (RAG) with LanceDB"
 authors = [{ name = "Yiorgis Gozadinos", email = "ggozadinos@gmail.com" }]
 license = { text = "MIT" }
 readme = { file = "README.md", content-type = "text/markdown" }
-requires-python = ">=3.11"
-keywords = ["RAG", "sqlite", "sqlite-vec", "ml", "mcp"]
+requires-python = ">=3.12"
+keywords = ["RAG", "lancedb", "vector-database", "ml", "mcp"]
 classifiers = [
     "Development Status :: 4 - Beta",
     "Environment :: Console",
@@ -22,17 +22,17 @@ classifiers = [
 ]
 
 dependencies = [
-    "docling>=2.15.0",
+    "docling>=2.49.0",
     "fastmcp>=2.8.1",
     "httpx>=0.28.1",
+    "lancedb>=0.24.3",
     "ollama>=0.5.3",
     "pydantic>=2.11.7",
-    "pydantic-ai>=0.7.2",
+    "pydantic-ai>=0.8.1",
     "python-dotenv>=1.1.0",
-    "rich>=14.0.0",
-    "sqlite-vec>=0.1.6",
-    "tiktoken>=0.9.0",
-    "typer>=0.16.0",
+    "rich>=14.1.0",
+    "tiktoken>=0.11.0",
+    "typer>=0.16.1",
     "watchfiles>=1.1.0",
 ]
 
@@ -56,7 +56,7 @@ dev = [
     "mkdocs>=1.6.1",
     "mkdocs-material>=9.6.14",
     "pre-commit>=4.2.0",
-    "pyright>=1.1.403",
+    "pyright>=1.1.404",
     "pytest>=8.4.0",
     "pytest-asyncio>=1.0.0",
     "pytest-cov>=6.2.1",

{haiku_rag-0.6.0 → haiku_rag-0.7.1}/src/haiku/rag/app.py

@@ -40,7 +40,7 @@ class HaikuRAGApp:
                 f"[b]Document with id [cyan]{doc.id}[/cyan] added successfully.[/b]"
             )
 
-    async def get_document(self, doc_id: int):
+    async def get_document(self, doc_id: str):
         async with HaikuRAG(db_path=self.db_path) as self.client:
             doc = await self.client.get_document_by_id(doc_id)
             if doc is None:
@@ -48,14 +48,14 @@ class HaikuRAGApp:
                 return
             self._rich_print_document(doc, truncate=False)
 
-    async def delete_document(self, doc_id: int):
+    async def delete_document(self, doc_id: str):
         async with HaikuRAG(db_path=self.db_path) as self.client:
             await self.client.delete_document(doc_id)
             self.console.print(f"[b]Document {doc_id} deleted successfully.[/b]")
 
-    async def search(self, query: str, limit: int = 5, k: int = 60):
+    async def search(self, query: str, limit: int = 5):
         async with HaikuRAG(db_path=self.db_path) as self.client:
-            results = await self.client.search(query, limit=limit, k=k)
+            results = await self.client.search(query, limit=limit)
             if not results:
                 self.console.print("[red]No results found.[/red]")
                 return