Merge pull request #2 from Shakshi3104/feature

Dockerfile

@@ -0,0 +1,21 @@
+FROM python:3.11
+
+# copy requirements
+COPY requirements.txt requirements.txt
+
+# install
+RUN apt-get update && apt-get clean;
+RUN apt-get install -y libgl1-mesa-dev
+RUN apt-get install -y libssl-dev
+
+RUN pip install --upgrade pip
+RUN pip install -r requirements.txt
+
+COPY .env .env
+COPY model/ model/
+# COPY view/ view/
+COPY app.py app.py
+
+ENV PYTHONUNBUFFERED 1
+
+CMD gradio app.py

README.md

@@ -2,6 +2,16 @@
 
 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.
+
+```bash
+docker compose up --build
+```
+and, access to http://localhost:7860/
+
+![](./materials/cobalt-gradio-demo.png)
+
 ## Usage
 
 ```python

app.py

@@ -0,0 +1,50 @@
+import gradio as gr
+import pandas as pd
+
+from model.search.hybrid import HybridSearchClient
+from model.data.notion_db import fetch_sakurap_corpus
+
+
+def search(search_client: HybridSearchClient):
+    def _search(query: str) -> pd.DataFrame:
+        results = search_client.search_top_n(query)
+        result = results[0]
+        result["rank"] = result["rank"] + 1
+        result = result[["rank", "title", "content", "rank_sparse", "rank_dense"]]
+        result.columns = ["rank", "title", "rap lyric", "rank: surface", "rank: vector"]
+        return result
+
+    return _search
+
+
+if __name__ == "__main__":
+    # Load dataset
+    sakurap_df = fetch_sakurap_corpus("./data/sakurap_corpus.csv")
+    # Initialize search client
+    search_client = HybridSearchClient.from_dataframe(sakurap_df, "content")
+
+    with gr.Blocks() as search_interface:
+        gr.Markdown("""
+        # 💎 Cobalt
+        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/).
+        """)
+        # Input query
+        search_query = gr.Textbox(label="Query", submit_btn=True)
+
+        gr.Markdown("""
+        ## Search Results
+
+        """)
+        # Search result
+        result_table = gr.DataFrame(label="Result",
+                                    column_widths=["5%", "20%", "65%", "5%", "5%"],
+                                    wrap=True,
+                                    datatype=["str", "str", "markdown", "str", "str"],
+                                    interactive=False)
+
+        # Event handler
+        search_query.submit(fn=search(search_client), inputs=search_query, outputs=result_table)
+
+    # App launch
+    search_interface.queue()
+    search_interface.launch(server_name="0.0.0.0")

compose.yml

@@ -0,0 +1,12 @@
+services:
+  cobalt:
+    container_name: cobalt-hybrid-search
+    build:
+      context: .
+      dockerfile: Dockerfile
+    ports:
+      - "7860:7860"
+    volumes:
+      - type: bind
+        source: ./model
+        target: /model