Add files

app.py

@@ -0,0 +1,76 @@
+from map_search import query_data
+import gradio as gr
+from gradio.themes.base import Base
+import pandas as pd
+import plotly.graph_objects as go
+
+def query_data_with_map(question):
+    if question:
+        # Assuming query_data returns a tuple: (list_of_arrays, text_from_gemini)
+        list_of_arrays, text_from_gemini = query_data(question)
+        
+        # Convert list_of_arrays to a DataFrame
+        df = pd.DataFrame(list_of_arrays, columns=['title', 'chalet_title', 'final_price', 'unit_custom_title', 'lat', 'lng'])
+        
+        text_list = [(row['title'], row['unit_custom_title'], row['chalet_title'], row['final_price']) for index, row in df.iterrows()]
+        fig = go.Figure(go.Scattermapbox(
+            customdata=text_list,
+            lat=df['lat'].tolist(),
+            lon=df['lng'].tolist(),
+            mode='markers',
+            marker=go.scattermapbox.Marker(
+                size=6
+            ),
+            hoverinfo="text",
+            hovertemplate=(
+                '<b>Title</b>: %{customdata[0]}<br>'
+                '<b>Unit Custom Title</b>: %{customdata[1]}<br>'
+                '<b>Chalet Title</b>: %{customdata[2]}<br>'
+                '<b>Final Price</b>: SAR %{customdata[3]}'
+            )
+        ))
+    else:
+        # Create an empty map
+        fig = go.Figure(go.Scattermapbox(
+            lat=[],
+            lon=[],
+            mode='markers',
+            marker=go.scattermapbox.Marker(
+                size=20
+            )
+        ))
+        text_from_gemini = ""
+
+    fig.update_layout(
+        mapbox_style="open-street-map",
+        hovermode='closest',
+        mapbox=dict(
+            bearing=0,
+            center=go.layout.mapbox.Center(
+                lat=24.7136,  # Latitude for Riyadh
+                lon=46.6753   # Longitude for Riyadh
+            ),
+            pitch=0,
+            zoom=10
+        )
+    )
+    return fig, text_from_gemini
+
+with gr.Blocks(theme=Base(), title="Riyadh Entertainment Map powered by Smart Search System using Vector Search + RAG") as demo:
+    gr.Markdown(
+        """
+        # Smart Search System using Atlas Vector Search + RAG Architecture
+        """)
+    textbox = gr.Textbox(label="Enter your query here", lines=1)
+    with gr.Row():
+        button = gr.Button("Search", variant="primary")
+    with gr.Column():
+        output1 = gr.Plot(label="Map Output")
+        output2 = gr.Textbox(lines=1, max_lines=10, label="Output generated by chaining Atlas Vector Search to Langchain's `load_qa_chain` + Gemini flash 1.5 LLM:")
+
+    # Load the empty map when the app starts
+    demo.load(query_data_with_map, inputs=[textbox], outputs=[output1, output2])
+    # Call query_data_with_map function upon clicking the Submit button
+    button.click(query_data_with_map, textbox, outputs=[output1, output2])
+
+demo.launch(share=True)

map_search.py

@@ -0,0 +1,134 @@
+import json
+from pymongo import MongoClient
+from langchain_google_genai import GoogleGenerativeAIEmbeddings, ChatGoogleGenerativeAI
+from langchain_community.vectorstores import MongoDBAtlasVectorSearch
+from langchain.chains.question_answering import load_qa_chain
+from langchain.schema import Document
+from langchain.prompts import PromptTemplate
+import env  # Ensure key_param contains MongoDB URI and Google API key
+
+google_api_key = env.GOOGLE_API_KEY
+
+# Load data from JSON file
+def load_data(filepath):
+    with open(filepath, 'r', encoding='utf-8') as file:
+        data = json.load(file)
+    return data
+
+# Convert JSON entries to Document format for embeddings
+def json_to_documents(data):
+    documents = []
+    for entry in data:
+        # Extract key fields to create a full text for embedding
+        title = entry.get("title", "")
+        chalet_title = entry.get("chalet_title", "")
+        description = entry.get("description", "")
+        chalet = entry.get("chalet", {})
+        chalet_title_full = chalet.get("title", "")
+        address_city = chalet.get("address", {}).get("city", "")
+        address_area = chalet.get("address", {}).get("area", "")
+        total_review_points = chalet.get("totalReview", {}).get("points", "")
+        total_review_text = chalet.get("totalReview", {}).get("text", "")
+        cancel_policy = chalet.get("cancelPolicy", "")
+        unit_custom_title = entry.get("unit_custom_title", "")
+        checkin_hour = entry.get("checkinHour", "")
+        checkout_hour = entry.get("checkoutHour", "")
+        final_price = entry.get("final_price", "")
+        
+        extra_description = entry.get("extraDescription", [])
+        extra_description_text = "\n".join(
+            [f"{desc['header']}: {', '.join(desc['content'])}" for desc in extra_description]
+        )
+        
+        full_text = (
+            f"{title}\n"
+            f"{chalet_title}\n"
+            f"{description}\n"
+            f"{chalet_title_full}\n"
+            f"{address_city}\n"
+            f"{address_area}\n"
+            f"التقييم: {total_review_points}\n"
+            f"اجمالي التقييم: {total_review_text}\n"
+            f"شروط الغاء الحجز: {cancel_policy}\n"
+            f"{unit_custom_title}\n"
+            f"تسجيل دخول: {checkin_hour}\n"
+            f"تسجيل خروج: {checkout_hour}\n"
+            f"السعر: {final_price}\n"
+            f"{extra_description_text}"
+        )
+        
+        # Create Document object with text and metadata
+        documents.append(Document(page_content=full_text, metadata=entry))
+    return documents
+
+
+# MongoDB setup
+client = MongoClient(env.MONGO_URI)
+db = "riyadhMap"
+collectionName = "mapData"
+collection = client[db][collectionName]
+
+embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=google_api_key)
+
+# NOTE: the following code used to load data from JSON file and create a vector store. 
+# data = load_data("data.json")
+# documents = json_to_documents(data)
+# vectorStore = MongoDBAtlasVectorSearch.from_documents(documents, embeddings, collection=collection)
+
+
+vectorStore = MongoDBAtlasVectorSearch(collection, embeddings)
+
+# Language Model for RetrievalQA
+llm = ChatGoogleGenerativeAI(model="gemini-1.5-flash", google_api_key=google_api_key)
+
+prompt_template = """
+As a friendly tourism agent, suggest the best possible options based on the client's input. Your answer should be based on the text input language but mostly in Arabic or English. If there is no exact match, provide the top three closest possible information. Each context will provide `title` (e.g. كود الوحدة (xxxxx)), therefore, always include `title` in your answer for better user experience from the `context`. Be convincing and friendly in your response and use Saudi accent if the text in Arabic.\n\n
+Context:\n{context}\n
+Question:\n{question}\n
+Answer:
+"""
+
+prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
+
+# Use the custom prompt with RetrievalQA to guide the model
+retriever = vectorStore.as_retriever()
+qa = load_qa_chain(llm, chain_type="stuff", prompt=prompt)
+
+# Define a query function for vector-based similarity search and RAG
+def query_data(query):
+    # Perform similarity search
+    docs = vectorStore.similarity_search(query, k=10)  # Increase the number of retrieved documents
+    
+    # Join document content for RAG context
+    context = "\n\n".join([doc.page_content for doc in docs]) if docs else "No relevant documents found."
+    properties = []
+    for doc in docs:
+        metadata = doc.metadata
+        details = {
+            "title": metadata.get("title", ""),
+            "chalet_title": metadata.get("chalet_title", ""),
+            "final_price": metadata.get("final_price", ""),
+            "address": metadata.get("chalet", {}).get("address", {}).get("city", ""),
+            "area": metadata.get("chalet", {}).get("address", {}).get("area", ""),
+            "total_review_points": metadata.get("chalet", {}).get("totalReview", {}).get("points", ""),
+            "total_review_text": metadata.get("chalet", {}).get("totalReview", {}).get("text", ""),
+            "cancel_policy": metadata.get("chalet", {}).get("cancelPolicy", ""),
+            "unit_custom_title": metadata.get("unit_custom_title", ""),
+            "checkin_hour": metadata.get("checkinHour", ""),
+            "checkout_hour": metadata.get("checkoutHour", ""),
+            "extra_description": metadata.get("extraDescription", []),
+            "lat": metadata.get("chalet", {}).get("lat", ""),
+            "lng": metadata.get("chalet", {}).get("lng", "")
+        }
+        properties.append(details)
+
+    # Generate QA response with RAG
+    retriever_output = qa.run(input_documents=docs, question=query)
+    return properties, retriever_output
+
+# Example of querying the data
+# query = "شقة قريبة من البوليفارد بسعر مناسب ريال غرفتين نوم مع تسجيل دخول ذاتي"
+# as_output, retriever_output = query_data(query)
+
+# print("Atlas Vector Search Output: ", as_output)
+# print("RAG QA Output: ", retriever_output)

requirements.txt

@@ -0,0 +1,100 @@
+aiofiles==23.2.1
+aiohappyeyeballs==2.4.3
+aiohttp==3.10.10
+aiosignal==1.3.1
+annotated-types==0.7.0
+anyio==4.6.2.post1
+attrs==24.2.0
+cachetools==5.5.0
+certifi==2024.8.30
+charset-normalizer==3.4.0
+click==8.1.7
+colorama==0.4.6
+dataclasses-json==0.6.7
+dnspython==2.7.0
+fastapi==0.115.4
+ffmpy==0.4.0
+filelock==3.16.1
+frozenlist==1.5.0
+fsspec==2024.10.0
+google-ai-generativelanguage==0.6.10
+google-api-core==2.23.0
+google-api-python-client==2.151.0
+google-auth==2.36.0
+google-auth-httplib2==0.2.0
+google-generativeai==0.8.3
+googleapis-common-protos==1.65.0
+gradio==5.5.0
+gradio-client==1.4.2
+greenlet==3.1.1
+grpcio==1.67.1
+grpcio-status==1.67.1
+h11==0.14.0
+httpcore==1.0.6
+httplib2==0.22.0
+httpx==0.27.2
+httpx-sse==0.4.0
+huggingface-hub==0.26.2
+idna==3.10
+jinja2==3.1.4
+jsonpatch==1.33
+jsonpointer==3.0.0
+langchain==0.3.7
+langchain-community==0.3.5
+langchain-core==0.3.15
+langchain-google-genai==2.0.4
+langchain-text-splitters==0.3.2
+langsmith==0.1.142
+markdown-it-py==3.0.0
+markupsafe==2.1.5
+marshmallow==3.23.1
+mdurl==0.1.2
+multidict==6.1.0
+mypy-extensions==1.0.0
+numpy==1.26.4
+orjson==3.10.11
+packaging==24.2
+pandas==2.2.3
+pillow==11.0.0
+plotly==5.24.1
+propcache==0.2.0
+proto-plus==1.25.0
+protobuf==5.28.3
+pyasn1==0.6.1
+pyasn1-modules==0.4.1
+pydantic==2.9.2
+pydantic-core==2.23.4
+pydantic-settings==2.6.1
+pydub==0.25.1
+pygments==2.18.0
+pymongo==4.10.1
+pyparsing==3.2.0
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-multipart==0.0.12
+pytz==2024.2
+pyyaml==6.0.2
+requests==2.32.3
+requests-toolbelt==1.0.0
+rich==13.9.4
+rsa==4.9
+ruff==0.7.3
+safehttpx==0.1.1
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+sqlalchemy==2.0.35
+starlette==0.41.2
+tenacity==9.0.0
+tomlkit==0.12.0
+tqdm==4.67.0
+typer==0.13.0
+typing-extensions==4.12.2
+typing-inspect==0.9.0
+tzdata==2024.2
+uritemplate==4.1.1
+urllib3==2.2.3
+uvicorn==0.32.0
+websockets==12.0
+yarl==1.17.1