File size: 2,585 Bytes
3d0f7c4
 
 
 
abfd83b
 
c51711e
5d4ec37
 
c51711e
3d0f7c4
 
 
 
c51711e
3d0f7c4
 
c51711e
 
3d0f7c4
 
 
 
 
ddcad02
3d0f7c4
 
 
 
 
ddcad02
 
 
3d0f7c4
c51711e
ddcad02
3d0f7c4
 
 
 
c51711e
3d0f7c4
 
 
 
c51711e
3d0f7c4
 
c51711e
ddcad02
 
c51711e
 
791b656
c51711e
3d0f7c4
 
 
 
 
 
c51711e
3d0f7c4
 
 
 
 
 
ddcad02
c51711e
3d0f7c4
 
 
c51711e
ddcad02
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
import streamlit as st
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
import os
from dotenv import load_dotenv

# Load environment variables
load_dotenv()
api_key = os.getenv("api_key")

# App title and description
st.title("I am Your GrowBuddy 🌱")
st.write("Let me help you start gardening. Let's grow together!")

# Function to load model
def load_model():
    try:
        tokenizer = AutoTokenizer.from_pretrained("KhunPop/Gardening", use_auth_token=api_key)
        model = AutoModelForCausalLM.from_pretrained("QuantFactory/leniachat-gemma-2b-v0-GGUF", use_auth_token=api_key)
        return tokenizer, model
    except Exception as e:
        st.error(f"Failed to load model: {e}")
        return None, None

# Load model and tokenizer
tokenizer, model = load_model()

if not tokenizer or not model:
    st.stop()

# Default to CPU, or use GPU if available
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = model.to(device)

# Initialize session state messages
if "messages" not in st.session_state:
    st.session_state.messages = [
        {"role": "assistant", "content": "Hello there! How can I help you with gardening today?"}
    ]

# Display conversation history
for message in st.session_state.messages:
    with st.chat_message(message["role"]):
        st.write(message["content"])

# Function to generate response
def generate_response(prompt):
    try:
        # Tokenize input prompt with dynamic padding and truncation
        inputs = tokenizer(prompt, return_tensors="pt", truncation=True, padding=True, max_length=512).to(device)

        # Generate output from model
        outputs = model.generate(inputs["input_ids"], max_new_tokens=100, temperature=0.7, do_sample=True)

        # Decode and return response
        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
        return response
    except Exception as e:
        st.error(f"Error during text generation: {e}")
        return "Sorry, I couldn't process your request."

# User input field for gardening questions
user_input = st.chat_input("Type your gardening question here:")

if user_input:
    with st.chat_message("user"):
        st.write(user_input)

    with st.chat_message("assistant"):
        with st.spinner("Generating your answer..."):
            response = generate_response(user_input)
            st.write(response)

    # Update session state
    st.session_state.messages.append({"role": "user", "content": user_input})
    st.session_state.messages.append({"role": "assistant", "content": response})