Update app.py

app.py

@@ -1,65 +1,183 @@
 import gradio as gr
+import openai
+from langchain.chains import RetrievalQA
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.document_loaders import TextLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.llms import OpenAI
+import os
 
-# Define Gradio theme with valid color shortcuts and custom fonts
-theme = gr.themes.Soft(
-    primary_hue="indigo",
-    secondary_hue="emerald",
-    neutral_hue="gray",
-    font=["Rubik"]  # Correctly passing as a list or using GoogleFont
+OPENAI_API_KEYS = os.getenv("OPENAI_API_KEYS")
+
+# Knowledge base for Crustdata APIs
+docs = """
+# Crustdata Dataset API
+
+## Description
+The Crustdata Dataset API provides access to a wide variety of datasets across different domains. It allows users to search, filter, and retrieve datasets based on categories, tags, and other metadata.
+
+## Key Endpoints
+
+### 1. **GET /datasets**
+- **Description**: Retrieves a list of available datasets.
+- **Parameters**:
+  - `category` (optional): Filter datasets by a specific category.
+  - `tags` (optional): Filter datasets by tags (comma-separated).
+  - `limit` (optional): Maximum number of datasets to return (default: 10).
+
+- **Example Request**:
+  ```bash
+  curl -X GET "https://api.crustdata.com/datasets?category=finance&tags=economy,stocks&limit=5"
+  ```
+
+- **Example Response**:
+  ```json
+  {
+    "datasets": [
+      {
+        "id": "12345",
+        "name": "Global Finance Dataset",
+        "category": "finance",
+        "tags": ["economy", "stocks"]
+      },
+      ...
+    ]
+  }
+  ```
+
+### 2. **GET /datasets/{id}**
+- **Description**: Retrieves detailed information about a specific dataset.
+- **Parameters**:
+  - `id` (required): The unique identifier of the dataset.
+
+- **Example Request**:
+  ```bash
+  curl -X GET "https://api.crustdata.com/datasets/12345"
+  ```
+
+- **Example Response**:
+  ```json
+  {
+    "id": "12345",
+    "name": "Global Finance Dataset",
+    "description": "A comprehensive dataset on global financial markets.",
+    "category": "finance",
+    "tags": ["economy", "stocks"],
+    "source": "World Bank"
+  }
+  ```
+
+---
+
+# Crustdata Discovery and Enrichment API
+
+## Description
+The Crustdata Discovery and Enrichment API allows users to enrich their datasets by adding metadata, geolocation information, and other relevant attributes.
+
+## Key Endpoints
+
+### 1. **POST /enrich**
+- **Description**: Enriches input data with additional metadata based on the specified enrichment type.
+- **Parameters**:
+  - `input_data` (required): A list of data entries to be enriched.
+  - `enrichment_type` (required): The type of enrichment to apply. Supported types:
+    - `geolocation`
+    - `demographics`
+
+- **Example Request**:
+  ```bash
+  curl -X POST "https://api.crustdata.com/enrich" \
+    -H "Content-Type: application/json" \
+    -d '{
+          "input_data": [{"address": "123 Main St, Springfield"}],
+          "enrichment_type": "geolocation"
+        }'
+  ```
+
+- **Example Response**:
+  ```json
+  {
+    "enriched_data": [
+      {
+        "address": "123 Main St, Springfield",
+        "latitude": 37.12345,
+        "longitude": -93.12345
+      }
+    ]
+  }
+  ```
+
+### 2. **POST /search**
+- **Description**: Searches for relevant metadata or datasets based on user-provided criteria.
+- **Parameters**:
+  - `query` (required): The search term or query string.
+  - `filters` (optional): Additional filters to narrow down the search results.
+  
+- **Example Request**:
+  ```bash
+  curl -X POST "https://api.crustdata.com/search" \
+    -H "Content-Type: application/json" \
+    -d '{
+          "query": "energy consumption",
+          "filters": {"category": "energy"}
+        }'
+  ```
+
+- **Example Response**:
+  ```json
+  {
+    "results": [
+      {
+        "id": "67890",
+        "name": "Energy Consumption Dataset",
+        "category": "energy",
+        "tags": ["consumption", "renewables"]
+      }
+    ]
+  }
+  ```
+
+---
+
+# General Notes
+- All endpoints require authentication using an API key.
+- API requests must include the `Authorization` header:
+  ```plaintext
+  Authorization: Bearer YOUR_API_KEY
+  ```
+- Response format: JSON
+- Base URL: `https://api.crustdata.com`
+"""
+
+# Split the documentation into chunks for embedding
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+doc_chunks = text_splitter.create_documents([docs])
+
+# Embed the documents using OpenAI embeddings
+embeddings = OpenAIEmbeddings()
+docsearch = FAISS.from_documents(doc_chunks, embeddings)
+
+# Create a QA chain
+qa_chain = RetrievalQA.from_chain_type(
+    llm=OpenAI(model="gpt-3.5-turbo"),
+    retriever=docsearch.as_retriever(),
+    return_source_documents=True
+)
+
+# Function to handle user queries
+def answer_question(question):
+    result = qa_chain.run(question)
+    return result
+
+# Create a Gradio interface
+chat_interface = gr.Interface(
+    fn=answer_question,
+    inputs=gr.Textbox(lines=2, placeholder="Ask a question about Crustdata APIs..."),
+    outputs="text",
+    title="Crustdata API Chat",
+    description="Ask any technical questions about Crustdata’s Dataset and Discovery APIs.",
 )
 
-# Create Gradio blocks with custom CSS for enhanced UI
-with gr.Blocks(
-    theme=theme,
-    title="RocketGPT - AI-Powered Chatbot",
-    css="""
-        .gradio-container {background-color: #f0f4f8; padding: 20px;}
-        h1, h2, h3, h4, h5, h6 {color: #4a5568;}
-        .gradio-container .avatar-container {height: 40px; width: 40px; border-radius: 50%; overflow: hidden;}
-        #duplicate-button {margin: auto; color: white; background: #2d3748; border-radius: 100vh; padding: 8px 16px;}
-        .tab-nav-button {background-color: #e2e8f0; border-radius: 8px;}
-        .tab-nav-button.selected {background-color: #cbd5e0;}
-    """
-) as demo:
-    gr.Markdown("# 🚀 RocketGPT  - AI-Powered Chatbot")
-
-    # Define individual tabs as separate Blocks
-    with gr.Tabs():
-        with gr.Tab("💬 Chat"):
-            gr.HTML("""
-                <iframe src='https://Qwen-QwQ-32B-preview.hf.space' 
-                        width='100%' height='800px' 
-                        style='border-radius: 8px; border: none;'></iframe>
-            """)
-
-        with gr.Tab("🗣️ Speech Generator"):
-            gr.HTML("""
-                <iframe src='https://wifix199-Text-to-speech-LuminaIQ.hf.space' 
-                        width='100%' height='800px' 
-                        style='border-radius: 8px; border: none;'></iframe>
-            """)
-
-        with gr.Tab("🖼️ Image Generator"):
-            gr.HTML("""
-                <iframe src='https://wifix199-Text-to-image-LuminaIQ.hf.space' 
-                        width='100%' height='800px' 
-                        style='border-radius: 8px; border: none;'></iframe>
-            """)
-
-        with gr.Tab("🎥 Video Generator"):
-            gr.HTML("""
-                <iframe src='https://kingnish-instant-video.hf.space' 
-                        width='100%' height='800px' 
-                        style='border-radius: 8px; border: none;'></iframe>
-            """)
-
-        with gr.Tab("👨‍💻 Website Generator"):
-            gr.HTML("""
-                <iframe src='https://Qwen-Qwen2.5-Coder-Artifacts.hf.space' 
-                        width='100%' height='800px' 
-                        style='border-radius: 8px; border: none;'></iframe>
-            """)
-
-# Launch the app with queue support
-demo.queue(max_size=300)
-demo.launch()
+# Launch the Gradio app
+chat_interface.launch(share=True)