Update app.py

app.py

@@ -1,63 +1,59 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.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
-"""
-demo = 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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+from langchain.prompts import ChatPromptTemplate
+from langchain.chains import RetrievalQA, ConversationalRetrievalChain
+from langchain.memory import ConversationBufferMemory
+
+def rag_retriever(message, history, system_prompt, num_sources=4, temperature=0):
+    chat = ChatGroq(temperature=temperature, model_name="llama3-70b-8192", api_key=os.getenv("GROQ_API_KEY"))
+
+    prompt_template = ChatPromptTemplate.from_messages([
+        ("system", system_prompt+"""
+
+        Use the following pieces of context to answer the user's question.
+        ----------------
+        {context}"""),
+        ("human", "{question}")
+    ])
+
+    memory = ConversationBufferMemory(memory_key="chat_history", output_key="answer", return_messages=True)
+
+    retriever = store.as_retriever(search_type="similarity", search_kwargs={'k': num_sources})
+
+    chain = ConversationalRetrievalChain.from_llm(llm=chat,
+                                                  retriever=retriever,
+                                                  return_source_documents=True,
+                                                  memory=memory,
+                                                  combine_docs_chain_kwargs={"prompt": prompt_template})
+
+
+    output = chain.invoke({"question": message})
+
+    sources = ""
+    for doc in output['source_documents']:
+      source_content = doc.page_content.strip().replace("\r\n", " ").replace("\r", " ").replace("\n", " ")
+      sources += f'<span style="color:green">Страница: {doc.metadata["page"]+1}</span><br><span style="color:gray">{source_content}</span><br><br>'
+
+    response = f"""<h5>Отговор:</h5>{output['answer']}<br><h5>Източници:</h5>{sources}"""
+    return response
+
+
+rag = gr.ChatInterface(rag_retriever,
+                       examples=[["Каква е целта на настоящия регламент", "You are an expert assistant in Bulgarian regulations. Provide precise and clear answers. Provide a detailed and comprehensive answer, incorporating as much relevant information as possible. Always respond in Bulgarian, regardless of the language used in the question."],
+                                 ["Какво са Системите с ИИ", "You are an expert assistant in Bulgarian regulations. Provide precise and clear answers. Always respond in Bulgarian, regardless of the language used in the question."],
+                                 ["Какво е равнище на технологично развитие", "You are an expert assistant in Bulgarian regulations. Provide precise and clear answers. Always respond in Bulgarian, regardless of the language used in the question."]],
+                       title="Чатене с документа AI Act",
+                       description="Питайте каквото пожелаете, но пишете на български.",
+                       chatbot=gr.Chatbot(placeholder="<strong>Вашият личен AI Act помощник</strong><br>Питайте каквото пожелаете, но пишете на български."),
+                       textbox=gr.Textbox(placeholder="Задайте своя въпрос...", container=False, scale=7),
+                       retry_btn="Отново",
+                       undo_btn="Назад",
+                       clear_btn="Изчистете",
+                       submit_btn="Изпрати",
+                       additional_inputs=[gr.components.Textbox("You are an expert assistant in Bulgarian regulations. Provide precise and clear answers. Always respond in Bulgarian, regardless of the language used in the question.", label="System Prompt"),
+                                          gr.components.Slider(minimum=1, maximum=10, value=4, step=1, label="Брой препратки"),
+                                          gr.components.Slider(minimum=0, maximum=2, value=0, label="Креативност на модела", info="Ако е много високо моделът си измисля, но може да напише интересни неща."),],
+                       additional_inputs_accordion=gr.Accordion("Допълнителни настройки", open=False),
+                      )
+
+rag.launch()