Update app.py

app.py

@@ -1,20 +1,147 @@
 import streamlit as st
-from transformers import pipeline
+import pdfplumber, re
+from transformers import pipeline, AutoTokenizer
 
-def main():
-    sentiment_pipeline = pipeline(model="distilbert/distilbert-base-uncased-finetuned-sst-2-english")
+# ───────────────── Cached pipelines ────────────────────────────────────
+@st.cache_resource(ttl=86400)
+def load_pipes():
+    summarizer = pipeline("summarization",         model=SUMM_MODEL)
+    tokenizer  = AutoTokenizer.from_pretrained(    SUMM_MODEL)
+    sentiment  = pipeline("text-classification",   model=SENT_MODEL)
+    ner        = pipeline("token-classification",  model=NER_MODEL,
+                         aggregation_strategy="simple")
+    return summarizer, tokenizer, sentiment, ner
+
+# ───────────────── Helper functions ────────────────────────────────────
+def split_by_tokens(text, max_tokens):
+    words = re.split(r"(\s+)", text)
+    buf, n = "", 0
+    for w in words:
+        ln = len(TOK(w).input_ids)
+        if n + ln <= max_tokens:
+            buf, n = buf + w, n + ln
+        else:
+            yield buf.strip(); buf, n = w, ln
+    if buf.strip(): yield buf.strip()
+
+def summarise(text):
+    parts = list(split_by_tokens(text, MAX_TOK))
+    per_len = max(25, min(80, TARGET_WORDS // max(1, len(parts))))
+    first = [SUMMAR(p, max_length=per_len,
+                       min_length=per_len//2,
+                       do_sample=False)[0]["summary_text"]
+             for p in parts]
+    joined = " ".join(first)
+    if len(joined.split()) > TARGET_WORDS:
+        joined = SUMMAR(joined, max_length=TARGET_WORDS,
+                                 min_length=TARGET_WORDS//2,
+                                 do_sample=False)[0]["summary_text"]
+    return joined
+
+def shorten(summary, n):
+    s = summary.split(". ")
+    return (". ".join(s[:n]).rstrip(".") + ".") if len(s) > n else summary
+
+def extract_pdf(file):
+    txt=""
+    with pdfplumber.open(file) as pdf:
+        for p in pdf.pages: txt += p.extract_text() or ""
+    return txt
+
+def tag_entities(text):
+    tt = {"Organization":[], "Person":[], "Location":[], "Miscellaneous":[]}
+    for e in NER(text):
+        grp = {"ORG":"Organization","PER":"Person",
+               "LOC":"Location"}.get(e["entity_group"],"Miscellaneous")
+        tt[grp].append(e["word"])
+    return {k: sorted(set(v)) for k,v in tt.items() if v}
+
+# ───────────────── Main Part ───────────────────────────────────────
+st.set_page_config(page_title="Financial News Analyzer",
+                   page_icon="📰",
+                   layout="wide")
+st.title("📰 Financial News Analyzer")
+st.markdown("##### Instantly grasp news content, sentiment, and relevant entities")
+
+# models and other constant variables
+SUMM_MODEL   = "sshleifer/distilbart-cnn-12-6"
+SENT_MODEL   = "nynn/Fintuned_Sentiment"
+NER_MODEL    = "Babelscape/wikineural-multilingual-ner"
+SUMMAR, TOK, SENT_CLF, NER = load_pipes()
+
+MAX_TOK      = 1024
+TARGET_WORDS = 225
+LABEL_MAP    = {"LABEL_0":"Negative","LABEL_1":"Positive","LABEL_2":"Neutral"}
+COLOR_MAP    = {"Positive":"green","Negative":"red","Neutral":"gray"}
+
+# ───────────────── Sidebar input ───────────────────────────────────────
+with st.sidebar:
+    st.header("Input News to Analyze:")
+    txt_input   = st.text_area("Paste news article", height=150)
+    pdf_file    = st.file_uploader("Or upload PDF", type=["pdf"])
+    sent_count  = st.slider("Summary length (sentences)",
+                            min_value=1, max_value=5, value=3, step=1)
+    run_btn     = st.button("🔍 Analyze", use_container_width=True)
+
+raw_text = extract_pdf(pdf_file) if pdf_file else txt_input.strip()
+
+# ───────────────── Main pipeline ───────────────────────────────────────
+if run_btn:
+    if not raw_text:
+        st.warning("Please provide text or a PDF first.")
+        st.stop()
+
+    with st.spinner("Analyzing"):
+        full_sum = summarise(raw_text)
+        summary  = shorten(full_sum, sent_count)
+
+    cols = st.columns([2,1])
+    with cols[0]:
+        st.subheader("📝 Summary")
+        st.write(summary)
+
+    with cols[1]:
+        res   = SENT_CLF(summary)[0]
+        label = LABEL_MAP.get(res["label"], res["label"])
+        colour= COLOR_MAP[label]
+        st.subheader("📊 Sentiment")
+        st.markdown(f"<h3 style='color:{colour};margin-bottom:0'>{label}</h3>"
+                    f"{res['score']*100:.1f}% Confidence</p>",
+                    unsafe_allow_html=True)
+
+    tags = tag_entities(summary)
+    st.subheader("🏷️ Relevant Tags")
+
+    if tags:
+        # CSS for the badge pills
+        pill_css = """
+        <style>
+        .tag-pill {
+          display: inline-block;
+          background: #f0f2f6;
+          color: #333;
+          padding: 4px 10px;
+          margin: 2px 4px 2px 0;
+          border-radius: 12px;
+          font-size: 0.9em;
+        }
+        .tag-cat {
+          font-weight: 600;
+          margin-top: 0;
+          margin-bottom: 4px;
+        }
+        </style>
+        """
+        st.markdown(pill_css, unsafe_allow_html=True)
+
+        # Render each category as a header + pills
+        for category, vals in tags.items():
+            st.markdown(f"<div class='tag-cat'>{category}</div>", unsafe_allow_html=True)
+            pills = "".join(f"<span class='tag-pill'>{v}</span>" for v in vals)
+            st.markdown(pills, unsafe_allow_html=True)
+    else:
+        st.info("No entities detected.")
 
-    st.title("Sentiment Analysis with HuggingFace Spaces")
-    st.write("Enter a sentence to analyze its sentiment:")
 
-    user_input = st.text_input("")
-    if user_input:
-        result = sentiment_pipeline(user_input)
-        sentiment = result[0]["label"]
-        confidence = result[0]["score"]
 
-        st.write(f"Sentiment: {sentiment}")
-        st.write(f"Confidence: {confidence:.2f}")
 
-if __name__ == "__main__":
-    main()