Move RAG modules into src and update Streamlit app

ingest.py → src/ingest.py

@@ -4,8 +4,8 @@ import pdfplumber
 from sentence_transformers import SentenceTransformer
 import faiss
 
-PDF_DIR = "data"
-IMAGE_DIR = "data/images"
+PDF_DIR = "src/data"
+IMAGE_DIR = "src/data/images"
 INDEX_DIR = "index"
 
 os.makedirs(IMAGE_DIR, exist_ok=True)

rag.py → src/rag.py

@@ -2,22 +2,20 @@ import os
 import pickle
 import faiss
 import numpy as np
-from dotenv import load_dotenv
 from sentence_transformers import SentenceTransformer
 from groq import Groq
 
 # ---------------- CONFIG ----------------
-INDEX_DIR = "index"
+INDEX_DIR = "src/index"
 TOP_K = 4
 
-# ---------------- LOAD ENV ----------------
-load_dotenv()
+# ---------------- GROQ CLIENT ----------------
+GROQ_API_KEY = os.environ.get("GROQ_API_KEY")
 
-api_key = os.getenv("GROQ_API_KEY")
-if not api_key:
-    raise ValueError("❌ GROQ_API_KEY not found in .env")
+if not GROQ_API_KEY:
+    raise RuntimeError("❌ GROQ_API_KEY not set in Hugging Face Secrets")
 
-client = Groq(api_key=api_key)
+client = Groq(api_key=GROQ_API_KEY)
 
 # ---------------- LOAD INDEX ----------------
 index = faiss.read_index(f"{INDEX_DIR}/faiss.index")
@@ -25,15 +23,11 @@ index = faiss.read_index(f"{INDEX_DIR}/faiss.index")
 with open(f"{INDEX_DIR}/documents.pkl", "rb") as f:
     documents = pickle.load(f)
 
-# ---------------- EMBEDDINGS ----------------
 embedder = SentenceTransformer("all-MiniLM-L6-v2")
 
-
-# ---------------- RETRIEVAL ----------------
+# ---------------- RETRIEVE ----------------
 def retrieve(query, top_k=TOP_K):
-    query_embedding = embedder.encode([query])
-    query_embedding = np.array(query_embedding).astype("float32")
-
+    query_embedding = embedder.encode([query]).astype("float32")
     distances, indices = index.search(query_embedding, top_k)
 
     results = []
@@ -44,7 +38,6 @@ def retrieve(query, top_k=TOP_K):
 
     return results
 
-
 # ---------------- LLM ----------------
 def ask_llm(query, contexts):
     context_text = "\n\n".join(
@@ -57,13 +50,7 @@ def ask_llm(query, contexts):
         messages=[
             {
                 "role": "system",
-                "content": """
-You are an astrology tutor.
-Explain concepts clearly and practically.
-If a chart or diagram from the reference material is useful,
-explicitly say: "Refer to the diagram below."
-Otherwise, do not mention diagrams.
-"""
+                "content": "You are an astrology tutor. Answer clearly and practically."
             },
             {
                 "role": "user",

src/streamlit_app.py

@@ -1,40 +1,41 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
-
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+from rag import retrieve, ask_llm
+import os
+
+st.set_page_config(
+    page_title="Only The Truth – Astrology Bot",
+    page_icon="🪐",
+    layout="wide"
+)
+
+st.title("🪐 Only The Truth – Astrology Assistant")
+
+st.markdown(
+    "Ask questions based on the astrology lessons and reference material."
+)
+
+# --- Input ---
+query = st.text_input("Ask your question")
+
+if query:
+    with st.spinner("🔍 Searching knowledge base..."):
+        contexts = retrieve(query)
+
+    with st.spinner("🧠 Generating answer..."):
+        answer = ask_llm(query, contexts)
+
+    # --- Answer ---
+    st.subheader("🪐 Answer")
+    st.write(answer)
+
+    # --- References ---
+    if contexts:
+        st.subheader("📘 References")
+        for c in contexts:
+            st.markdown(f"**{c['source']} — page {c['page']}**")
+
+            # Show images only if present and file exists
+            for img in c.get("images", []):
+                img_path = os.path.join("src", "data", "images", img)
+                if os.path.exists(img_path):
+                    st.image(img_path, use_column_width=True)