app.py

# app.py

import requests
import wikipedia
import gradio as gr
from transformers import pipeline

# 1) Load the BERT NER pipeline
ner = pipeline(
    "ner",
    model="dslim/bert-base-NER-uncased",
    grouped_entities=True
)

# 2) Geocode via Nominatim
def geocode(place: str):
    resp = requests.get(
        "https://nominatim.openstreetmap.org/search",
        params={"q": place, "format": "json", "limit": 1},
        headers={"User-Agent": "iVoiceContext/1.0"}
    )
    data = resp.json()
    if not data:
        return None
    return float(data[0]["lat"]), float(data[0]["lon"])

# 3) Fetch POIs via Overpass
def fetch_osm(lat, lon, osm_filter, limit=5):
    query = f"""
    [out:json][timeout:25];
    (
      node{osm_filter}(around:1000,{lat},{lon});
      way{osm_filter}(around:1000,{lat},{lon});
      rel{osm_filter}(around:1000,{lat},{lon});
    );
    out center {limit};
    """
    r = requests.post("https://overpass-api.de/api/interpreter", data={"data": query})
    elems = r.json().get("elements", [])
    items = []
    for e in elems:
        name = e.get("tags", {}).get("name")
        if name:
            items.append({"name": name})
    return items

# 4) Main function
def get_context(text: str):
    results = ner(text)
    # de-duplicate entities by text
    ents = {ent["word"]: ent["entity_group"] for ent in results}
    out = {}
    for word, label in ents.items():
        if label == "LOC":
            geo = geocode(word)
            if not geo:
                out[word] = {"type":"location", "error":"could not geocode"}
            else:
                lat, lon = geo
                out[word] = {
                    "type": "location",
                    "restaurants": fetch_osm(lat, lon, '["amenity"="restaurant"]'),
                    "attractions": fetch_osm(lat, lon, '["tourism"="attraction"]'),
                }
        else:
            # for PERSON, ORG, MISC, etc → Wikipedia
            try:
                summary = wikipedia.summary(word, sentences=2)
            except Exception:
                summary = "No summary available."
            out[word] = {"type": "wiki", "summary": summary}
    if not out:
        return {"error": "No entities found"}
    return out

# 5) Gradio UI
iface = gr.Interface(
    fn=get_context,
    inputs=gr.Textbox(lines=3, placeholder="Paste your translated text…"),
    outputs="json",
    title="iVoice Context-Aware",
    description="BERT NER → geocode LOC → Overpass POIs → Wikipedia for others"
)

if __name__ == "__main__":
    iface.launch()