File size: 5,063 Bytes
3cb87b9 917f4ef 3cb87b9 77b00cb 9b08bbc 4497ce8 77b00cb 3cb87b9 4497ce8 3cb87b9 de8fb8e 3cb87b9 77b00cb 3cb87b9 77b00cb 3cb87b9 77b00cb 3cb87b9 77b00cb 3cb87b9 9b08bbc 917f4ef 3cb87b9 917f4ef | 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 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 | import os
import tempfile
import streamlit as st
import PyPDF2
import faiss
import numpy as np
from sentence_transformers import SentenceTransformer
from groq import Groq
from gtts import gTTS
# 🚨 Must be the first Streamlit command
st.set_page_config(page_title="🌍 Climate Companion", layout="wide")
# Load model and Groq client once
@st.cache_resource
def load_model():
return SentenceTransformer("all-MiniLM-L6-v2")
@st.cache_resource
def load_groq_client():
return Groq(api_key=os.getenv("GROQ_API_KEY"))
embed_model = load_model()
client = load_groq_client()
# UI Header
st.markdown(
"<h1 style='text-align: center; color: #2E8B57;'>🌿 Climate Companion</h1>"
"<p style='text-align: center; font-size: 18px;'>Upload a climate report and ask environment-related questions.</p>",
unsafe_allow_html=True
)
# PDF uploader
uploaded_file = st.file_uploader("📄 Upload Climate Report (PDF)", type="pdf")
# Text chunking
def chunk_text(text, max_tokens=100, overlap=20):
words = text.split()
chunks = []
for i in range(0, len(words), max_tokens - overlap):
chunk = " ".join(words[i:i + max_tokens])
if chunk.strip():
chunks.append(chunk)
return chunks
# Process file only once per session
if uploaded_file:
if "processed_file" not in st.session_state or st.session_state.processed_file != uploaded_file.name:
with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file:
tmp_file.write(uploaded_file.read())
tmp_path = tmp_file.name
try:
with open(tmp_path, "rb") as f:
reader = PyPDF2.PdfReader(f)
full_text = "\n".join([page.extract_text() or "" for page in reader.pages])
except Exception as e:
st.error(f"❌ Failed to read PDF: {e}")
st.stop()
if not full_text.strip():
st.error("❌ No extractable text found in the PDF.")
st.stop()
st.success("✅ Extracted text from PDF successfully.")
# Chunk + Embed
with st.spinner("🔄 Chunking and embedding text..."):
chunks = chunk_text(full_text)
embeddings = embed_model.encode(chunks, show_progress_bar=True)
dimension = embeddings.shape[1]
index = faiss.IndexFlatL2(dimension)
index.add(np.array(embeddings).astype("float32"))
# Store in session_state
st.session_state.processed_file = uploaded_file.name
st.session_state.chunks = chunks
st.session_state.index = index
st.session_state.dimension = dimension
st.success(f"📚 {len(chunks)} text chunks embedded and indexed.")
else:
chunks = st.session_state.chunks
index = st.session_state.index
dimension = st.session_state.dimension
st.success("✅ Using cached embeddings from this session.")
# Question and Answer section
st.markdown("---")
st.subheader("🌱 Ask a Climate-Related Question")
col1, col2 = st.columns([5, 1])
question = col1.text_input("Enter your question here")
submit = col2.button("🔍 Get Answer")
if submit and question:
with st.spinner("🧠 Generating response..."):
q_embed = embed_model.encode([question])
_, indices = index.search(np.array(q_embed).astype("float32"), k=3)
top_chunks = [chunks[i] for i in indices[0]]
context = "\n".join(top_chunks)
prompt = f"""
You are a climate science expert. Use the context to answer the user's question concisely.
Context:
{context}
Question:
{question}
"""
try:
response = client.chat.completions.create(
model="llama3-8b-8192",
messages=[
{"role": "system", "content": "You are a helpful environmental scientist."},
{"role": "user", "content": prompt}
]
)
answer = response.choices[0].message.content.strip()
st.markdown("### ✅ Answer")
st.markdown(
f"<div style='background-color:#f0f9f5;padding:15px;border-radius:10px;'>{answer}</div>",
unsafe_allow_html=True,
)
st.markdown("### ✅ Wanna Hear")
# Generate and play audio response
try:
tts = gTTS(text=answer)
audio_path = os.path.join(tempfile.gettempdir(), "answer.mp3")
tts.save(audio_path)
st.audio(audio_path, format="audio/mp3")
except Exception as audio_err:
st.warning(f"🎤 Text-to-Speech error: {audio_err}")
with st.expander("📖 Context Used"):
st.code(context)
except Exception as e:
st.error(f"🚨 Error from Groq API: {e}")
else:
st.info("📤 Please upload a PDF to begin.")
|