[update] update README and others

README.md

@@ -1,51 +1,20 @@
 ---
 license: mit
-title: Cobalt
+title: Cobalt DuckDB
 sdk: gradio
-emoji: 💎
+emoji: 🦆
 colorFrom: blue
 colorTo: indigo
 pinned: false
 ---
 
-# Cobalt: Hybrid Search
+# Cobalt DuckDB
 
-Cobalt is a demo app for hybrid search with vector and surface search using [Ruri](https://huggingface.co/cl-nagoya/ruri-large), [BM25](https://github.com/dorianbrown/rank_bm25) and [Voyager](https://spotify.github.io/voyager/). The name cobalt is derived from the word 瑠璃 (Ruri), which refers to cobalt glass.
-
-## Demo
-This demo app is made by Gradio, deployed to [Hugging Face Space](https://huggingface.co/spaces/Shakshi3104/Cobalt).
-
-On local, you can run this app below:
-
-```bash
-docker compose up --build
-```
-and, access to http://localhost:7860/
-
-![](./materials/cobalt-gradio-demo.png)
-
-## Usage
-
-```python
-import pandas as pd
-from model.search.hybrid import HybridSearchClient
-
-# load documents from CSV file.
-df = pd.read_csv("corpus.csv")
-
-# Initialize search client
-# Specify column name to be searched. e.g. "content"
-search_client = HybridSearchClient.from_dataframe(df, "content")
-
-# Search documents from a query
-results = search_client.search_top_n("Arashi's history")
-
-```
+Cobalt is a demo app for vector search using [Ruri](https://huggingface.co/cl-nagoya/ruri-large) and DuckDB. The repository is a demo app similar to [cobalt-hybrid-search](https://github.com/Shakshi3104/cobalt-hybrid-search).
 
 ## Requirements
 
 - Python 3.10
-- rank_bm25
 - huggingface
-- voyager
+- duckdb
 - Other Python packages are refer to [requirements.txt](./requirements.txt)

compose.yml

@@ -1,6 +1,6 @@
 services:
   cobalt:
-    container_name: cobalt-hybrid-search
+    container_name: cobalt-duckdb
     build:
       context: .
       dockerfile: Dockerfile

requirements.txt

@@ -10,7 +10,6 @@ python-dotenv
 
 # Visualization
 gradio
-streamlit
 
 tqdm>=4.65
 matplotlib>=3.7