Add application file

app.py

@@ -0,0 +1,101 @@
+# app_pure_rag.py
+import numpy as np
+import faiss
+import gradio as gr
+from langchain.text_splitter import CharacterTextSplitter
+from sentence_transformers import SentenceTransformer
+
+# --- Load and Prepare Data ---
+with open("gen_agents.txt", "r", encoding="utf-8") as f:
+    full_text = f.read()
+
+# Split text into passages
+text_splitter = CharacterTextSplitter(separator="\n\n", chunk_size=512, chunk_overlap=20)
+docs = text_splitter.create_documents([full_text])
+passages = [doc.page_content for doc in docs]
+
+# Initialize embedder and build FAISS index
+embedder = SentenceTransformer('all-MiniLM-L6-v2')
+passage_embeddings = embedder.encode(passages, convert_to_tensor=False, show_progress_bar=True)
+passage_embeddings = np.array(passage_embeddings).astype("float32")
+d = passage_embeddings.shape[1]
+index = faiss.IndexFlatL2(d)
+index.add(passage_embeddings)
+
+# --- Provided Functions ---
+def retrieve_passages(query, embedder, index, passages, top_k=3):
+    """
+    Retrieve the top-k most relevant passages based on the query.
+    """
+    query_embedding = embedder.encode([query], convert_to_tensor=False)
+    query_embedding = np.array(query_embedding).astype('float32')
+    distances, indices = index.search(query_embedding, top_k)
+    retrieved = [passages[i] for i in indices[0]]
+    return retrieved
+
+# --- Gradio App Function ---
+def get_pure_rag_output(query):
+    retrieved = retrieve_passages(query, embedder, index, passages, top_k=3)
+    rag_text = "\n".join([f"Passage {i+1}: {p}" for i, p in enumerate(retrieved)])
+    # Wrap text in a styled div
+    return f"<div style='white-space: pre-wrap;'>{rag_text}</div>"
+
+def clear_output():
+    return ""
+
+# --- Custom CSS for a ChatGPT-like Dark Theme ---
+custom_css = """
+body {
+    background-color: #343541 !important;
+    color: #ECECEC !important;
+    margin: 0;
+    padding: 0;
+    font-family: 'Inter', sans-serif;
+}
+#container {
+    max-width: 900px;
+    margin: 0 auto;
+    padding: 20px;
+}
+label {
+    color: #ECECEC;
+    font-weight: 600;
+}
+textarea, input {
+    background-color: #40414F;
+    color: #ECECEC;
+    border: 1px solid #565869;
+}
+button {
+    background-color: #565869;
+    color: #ECECEC;
+    border: none;
+    font-weight: 600;
+    transition: background-color 0.2s ease;
+}
+button:hover {
+    background-color: #6e7283;
+}
+.output-box {
+    border: 1px solid #565869;
+    border-radius: 4px;
+    padding: 10px;
+    margin-top: 8px;
+    background-color: #40414F;
+}
+"""
+
+# --- Build Gradio Interface ---
+with gr.Blocks(css=custom_css) as demo:
+    with gr.Column(elem_id="container"):
+        gr.Markdown("## Pure RAG Output\nDisplays the retrieved passages from the corpus.")
+        query_input = gr.Textbox(label="Query", placeholder="Enter your query here...", lines=1)
+        with gr.Column():
+            submit_button = gr.Button("Submit")
+            clear_button = gr.Button("Clear")
+        output_box = gr.HTML(label="Retrieved Passages", elem_classes="output-box")
+        
+        submit_button.click(fn=get_pure_rag_output, inputs=query_input, outputs=output_box)
+        clear_button.click(fn=clear_output, inputs=[], outputs=output_box)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,6 @@
+gradio
+openai
+faiss-cpu
+sentence-transformers
+langchain
+numpy