Update app.py

app.py

@@ -1,69 +1,151 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from sentence_transformers import SentenceTransformer
+import faiss
+import numpy as np
 
+# -----------------------------
+# GLOBALS (simple in-memory store)
+# -----------------------------
+embedder = SentenceTransformer("all-MiniLM-L6-v2")
+vector_store = None
+documents = []
 
+
+# -----------------------------
+# DOCUMENT PROCESSING
+# -----------------------------
+def read_file(file):
+    text = ""
+
+    if file.name.endswith(".txt"):
+        text = file.read().decode("utf-8")
+
+    elif file.name.endswith(".pdf"):
+        import PyPDF2
+        reader = PyPDF2.PdfReader(file)
+        for page in reader.pages:
+            text += page.extract_text() + "\n"
+
+    elif file.name.endswith(".docx"):
+        import docx
+        doc = docx.Document(file)
+        for para in doc.paragraphs:
+            text += para.text + "\n"
+
+    return text
+
+
+def chunk_text(text, chunk_size=500):
+    chunks = []
+    for i in range(0, len(text), chunk_size):
+        chunks.append(text[i:i + chunk_size])
+    return chunks
+
+
+def process_document(file):
+    global vector_store, documents
+
+    text = read_file(file)
+    chunks = chunk_text(text)
+
+    embeddings = embedder.encode(chunks)
+
+    dim = embeddings.shape[1]
+    vector_store = faiss.IndexFlatL2(dim)
+    vector_store.add(np.array(embeddings))
+
+    documents = chunks
+
+    return f"Document processed: {len(chunks)} chunks created."
+
+
+# -----------------------------
+# RETRIEVAL
+# -----------------------------
+def retrieve(query, k=3):
+    global vector_store, documents
+
+    if vector_store is None:
+        return ""
+
+    query_embedding = embedder.encode([query])
+    distances, indices = vector_store.search(np.array(query_embedding), k)
+
+    retrieved_chunks = [documents[i] for i in indices[0]]
+    return "\n\n".join(retrieved_chunks)
+
+
+# -----------------------------
+# CHAT FUNCTION
+# -----------------------------
 def respond(
     message,
-    history: list[dict[str, str]],
+    history,
     system_message,
     max_tokens,
     temperature,
     top_p,
     hf_token: gr.OAuthToken,
 ):
-    """
-    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-    """
     client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
 
-    messages = [{"role": "system", "content": system_message}]
+    # 🔥 Retrieve relevant document context
+    context = retrieve(message)
 
-    messages.extend(history)
+    augmented_message = f"""
+Use the following context to answer the question.
+
+Context:
+{context}
+
+Question:
+{message}
+"""
 
-    messages.append({"role": "user", "content": message})
+    messages = [{"role": "system", "content": system_message}]
+    messages.extend(history)
+    messages.append({"role": "user", "content": augmented_message})
 
     response = ""
 
-    for message in client.chat_completion(
+    for chunk in client.chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        choices = message.choices
         token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+        if chunk.choices and chunk.choices[0].delta.content:
+            token = chunk.choices[0].delta.content
 
         response += token
         yield response
 
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
+# -----------------------------
+# UI
+# -----------------------------
 with gr.Blocks() as demo:
     with gr.Sidebar():
         gr.LoginButton()
-    chatbot.render()
+        file_upload = gr.File(label="Upload Document")
+        process_btn = gr.Button("Process Document")
+        status = gr.Textbox(label="Status")
+
+    chatbot = gr.ChatInterface(
+        respond,
+        additional_inputs=[
+            gr.Textbox(value="You are a helpful research assistant.", label="System message"),
+            gr.Slider(1, 2048, value=512, step=1, label="Max tokens"),
+            gr.Slider(0.1, 4.0, value=0.7, step=0.1, label="Temperature"),
+            gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-p"),
+        ],
+    )
+
+    process_btn.click(process_document, inputs=file_upload, outputs=status)
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()