Create app.py

app.py

@@ -1,63 +1,48 @@
 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()
+import pandas as pd
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Load the dataset
+df = pd.read_csv("climate_data.csv")  # Replace with your actual file name
+
+# Load the LLaMa model and tokenizer
+model_name = "huggingface/llama"  # Replace with actual LLaMa model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Function to get model responses
+def ask_llama(question):
+    inputs = tokenizer(question, return_tensors="pt")
+    outputs = model.generate(inputs.input_ids, max_length=100)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Function to fetch data from the dataset
+def fetch_data_from_dataset(query, df):
+    if "year" in query:
+        year = int(query.split("year")[-1].strip())
+        return df[df['year'] == year].to_dict(orient="records")
+    
+    if "scenario" in query:
+        scenario = query.split("scenario")[-1].strip()
+        columns = [col for col in df.columns if scenario in col]
+        return df[columns].to_dict(orient="records")
+    
+    return "Sorry, I couldn't find any relevant data."
+
+# Combined function to answer user questions
+def answer_question(query):
+    # Step 1: Get response from LLaMa model
+    llama_response = ask_llama(query)
+    
+    # Step 2: Fetch data based on response
+    data_response = fetch_data_from_dataset(llama_response, df)
+    
+    return data_response
+
+# Define the Gradio interface
+interface = gr.Interface(fn=answer_question, inputs="text", outputs="text", 
+                         title="Climate Data Explorer",
+                         description="Ask questions about climate data")
+
+# Launch the app
+interface.launch()