Create app.py

app.py

@@ -1,63 +1,89 @@
+import pandas as pd
+from PyPDF2 import PdfReader
+from docx import Document
+import os
+from groq import Groq
 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()
+
+# Function to read and process different document types
+def read_document(file):
+    try:
+        file_extension = os.path.splitext(file.name)[-1].lower()
+        print(f"Processing file: {file.name} with extension {file_extension}")
+        
+        if file_extension == '.txt':
+            return file.read().decode('utf-8')
+        elif file_extension == '.pdf':
+            reader = PdfReader(file)
+            text = ''
+            for page in reader.pages:
+                text += page.extract_text()
+            return text
+        elif file_extension == '.docx':
+            doc = Document(file)
+            return '\n'.join([paragraph.text for paragraph in doc.paragraphs])
+        elif file_extension in ['.csv', '.xls', '.xlsx']:
+            df = pd.read_excel(file) if file_extension != '.csv' else pd.read_csv(file)
+            return df.to_string(index=False)
+        else:
+            return "Unsupported file format"
+    except Exception as e:
+        print(f"Error processing file: {file.name} - {str(e)}")
+        return f"Error processing file: {file.name} - {str(e)}"
+
+# Set your API key as an environment variable
+GROQ_API_KEY = "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"  # Replace with your actual API key
+
+client = Groq()
+
+# Function to validate and truncate content to prevent API errors
+def validate_content(text):
+    # Basic validation to remove unwanted characters
+    validated_text = ''.join(e for e in text if e.isalnum() or e.isspace())
+    # Truncate text if it's too long
+    max_length = 8000  # Adjust as needed
+    if len(validated_text) > max_length:
+        validated_text = validated_text[:max_length] + "..."
+    return validated_text
+
+# Function to get an answer from the Groq API
+def get_answer(question, model="llama3-8b-8192"):
+    try:
+        chat_completion = client.chat.completions.create(
+            model=model,
+            messages=[{"role": "user", "content": question}],
+        )
+        return chat_completion.choices[0].message.content
+    except Exception as e:
+        print(f"Error in Groq API call: {str(e)}")
+        if hasattr(e, 'response'):
+            print(f"Full response: {e.response.json()}")
+        return f"Error in API call: {str(e)}"
+
+# Function to interface with the Gradio UI
+def chatbot_interface(documents, question):
+    text = ''
+    for doc in documents:
+        content = read_document(doc)
+        text += validate_content(content) + "\n\n"
+
+    answer = get_answer(f"{text}\n\nQuestion: {question}")
+    return answer
+
+# Gradio Interface
+with gr.Blocks(theme=gr.themes.Default(primary_hue="slate")) as demo:
+    gr.Markdown("# RAG-based Q/A Chatbot with Document Support", elem_id="title")
+    gr.Markdown("Upload documents and ask questions related to them.", elem_id="description")
+
+    with gr.Row():
+        with gr.Column():
+            doc_input = gr.File(file_count="multiple", label="Upload Documents")
+            question_input = gr.Textbox(label="Ask a Question")
+
+        with gr.Column():
+            output = gr.Textbox(label="Answer")
+
+    submit_button = gr.Button("Get Answer")
+    submit_button.click(chatbot_interface, inputs=[doc_input, question_input], outputs=output)
+
+demo.launch()