Update app.py

app.py

@@ -1,64 +1,93 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import os
+import PyPDF2
+import pandas as pd
+import openai
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.llms import OpenAI
 
-"""
-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 detect_language(text):
+    """Detects the language of the input text using OpenAI."""
+    response = openai.ChatCompletion.create(
+        model="gpt-3.5-turbo",
+        messages=[
+            {"role": "system", "content": "Detect the language of this text."},
+            {"role": "user", "content": text}
+        ]
+    )
+    return response["choices"][0]["message"]["content"].strip()
 
+# Set up OpenAI API key (replace with your key)
+openai.api_key = "YOUR_OPENAI_API_KEY"
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+def get_text_from_pdf(pdf_files):
+    text = ""
+    for pdf in pdf_files:
+        reader = PyPDF2.PdfReader(pdf)
+        for page in reader.pages:
+            text += page.extract_text() + "\n"
+    return text
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+def get_text_from_txt(txt_files):
+    text = ""
+    for txt in txt_files:
+        text += txt.read().decode("utf-8") + "\n"
+    return text
 
-    messages.append({"role": "user", "content": message})
+def get_text_from_csv(csv_files):
+    text = ""
+    for csv in csv_files:
+        df = pd.read_csv(csv)
+        text += df.to_string() + "\n"
+    return text
 
-    response = ""
+def create_vector_database(text):
+    splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+    texts = splitter.split_text(text)
+    embeddings = OpenAIEmbeddings()
+    vector_db = FAISS.from_texts(texts, embeddings)
+    return vector_db
 
-    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
+def get_answer(question, vector_db):
+    retriever = vector_db.as_retriever()
+    docs = retriever.get_relevant_documents(question)
+    
+    if not docs:
+        return "I could not find the answer in the documents. Do you want me to search external sources?"
+    
+    context = "\n".join([doc.page_content for doc in docs])
+    language = detect_language(question)
+    response = openai.ChatCompletion.create(
+        model="gpt-3.5-turbo",
+        messages=[
+            {"role": "system", "content": f"You are a Data Analytics assistant. Answer in {language}. Use the documents to answer questions."},
+            {"role": "user", "content": question + "\n\nBased on the following context:\n" + context}
+        ]
+    )
+    return response["choices"][0]["message"]["content"]
 
-        response += token
-        yield response
+def chatbot_interface(pdf_files, txt_files, csv_files, question):
+    text = ""
+    text += get_text_from_pdf(pdf_files) if pdf_files else ""
+    text += get_text_from_txt(txt_files) if txt_files else ""
+    text += get_text_from_csv(csv_files) if csv_files else ""
+    
+    if not text:
+        return "Please upload files before asking questions."
+    
+    vector_db = create_vector_database(text)
+    return get_answer(question, vector_db)
 
-
-"""
-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)",
-        ),
-    ],
+# Gradio interface
+demo = gr.Interface(
+    fn=chatbot_interface,
+    inputs=[gr.File(file_types=[".pdf"], multiple=True),
+            gr.File(file_types=[".txt"], multiple=True),
+            gr.File(file_types=[".csv"], multiple=True),
+            gr.Textbox(placeholder="Type your question here...")],
+    outputs=gr.Textbox()
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()