app.py

import streamlit as st
import pandas as pd
import numpy as np
import os
import requests
import json
import re

# — Page config
st.set_page_config(page_title="CSV-Backed AI Agent", layout="wide")

# — Title & image
st.title("CSV-Backed AI Agent")
st.image("./nadi-lok-image.png")

# — Load API key
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
if not OPENAI_API_KEY:
    st.error("❌ OPENAI_API_KEY not set in Settings → Secrets.")
    st.stop()

HEADERS = {
    "Authorization": f"Bearer {OPENAI_API_KEY}",
    "Content-Type": "application/json",
}

# — Sidebar: CSV upload & preview
st.sidebar.header("Upload CSV File")
uploaded_file = st.sidebar.file_uploader("Choose a CSV file", type="csv")

if uploaded_file:
    try:
        df = pd.read_csv(uploaded_file)
        st.sidebar.success("File uploaded successfully!")
        st.sidebar.write("Preview of the uploaded file:")
        st.sidebar.dataframe(df.head())
    except Exception as e:
        st.sidebar.error(f"Error reading file: {e}")
        df = None
else:
    df = None

if df is not None:
    st.markdown(f"**Loaded CSV:** {df.shape[0]} rows × {df.shape[1]} columns")

    @st.cache_data(show_spinner=False)
    def build_row_embeddings(df: pd.DataFrame):
        # 1) Convert each row to a compact JSON string
        texts = df.apply(lambda r: r.to_json(), axis=1).tolist()

        # 2) Batch‐call the embeddings endpoint
        embeddings = []
        for i in range(0, len(texts), 100):
            batch = texts[i : i + 100]
            resp = requests.post(
                "https://api.openai.com/v1/embeddings",
                headers=HEADERS,
                json={"model": "text-embedding-ada-002", "input": batch},
                timeout=60,
            )
            resp.raise_for_status()
            data = resp.json()["data"]
            embeddings.extend(d["embedding"] for d in data)

        return np.array(embeddings), texts

    embeddings, row_texts = build_row_embeddings(df)

# — Prompt input
prompt = st.text_area(
    "Enter your prompt for the agent",
    placeholder="e.g. Which products have price > 100?",
    height=150,
)

# — Run Agent
if st.button("Run Agent"):
    if df is None:
        st.error("Please upload a CSV file first.")
    elif not prompt.strip():
        st.error("Please enter a prompt.")
    else:
        # 1) Embed the prompt
        q_resp = requests.post(
            "https://api.openai.com/v1/embeddings",
            headers=HEADERS,
            json={"model": "text-embedding-ada-002", "input": [prompt]},
            timeout=60,
        )
        q_resp.raise_for_status()
        q_emb = np.array(q_resp.json()["data"][0]["embedding"])

        # 2) Compute cosine similarities
        norms = np.linalg.norm(embeddings, axis=1)
        q_norm = np.linalg.norm(q_emb)
        sims = embeddings.dot(q_emb) / (norms * q_norm + 1e-8)

        # 3) Select top-K relevant rows
        K = min(5, len(sims))
        top_idxs = sims.argsort()[-K:][::-1]
        relevant_rows = [row_texts[i] for i in top_idxs]

        # 4) Build the chat messages
        system_msg = {
            "role": "system",
            "content": (
                "You are an AI agent that reads the provided CSV rows and answers the user's query. "
                "Return your answer strictly as JSON (no extra explanation)."
            ),
        }
        memory_msg = {
            "role": "system",
            "content": "Relevant CSV rows:\n" + "\n".join(relevant_rows) + "\n<end of rows>",
        }
        user_msg = {"role": "user", "content": prompt}

        # 5) Call the Chat API
        chat_resp = requests.post(
            "https://api.openai.com/v1/chat/completions",
            headers=HEADERS,
            json={
                "model": "gpt-3.5-turbo",
                "messages": [system_msg, memory_msg, user_msg],
                "temperature": 0,
                "max_tokens": 1500,
            },
            timeout=60,
        )
        chat_resp.raise_for_status()
        answer = chat_resp.json()["choices"][0]["message"]["content"]

        # 6) Extract the JSON payload
        txt = re.sub(r"```(?:json)?", "", answer).strip()
        start = txt.find("{")
        end = txt.rfind("}") + 1
        parsed = None
        if start >= 0 and end > 0:
            frag = re.sub(r",\s*([}\]])", r"\1", txt[start:end])
            try:
                parsed = json.loads(frag)
            except json.JSONDecodeError:
                parsed = None

        # 7) Display results
        if parsed is not None:
            st.subheader("✅ JSON Output")
            st.json(parsed)
        else:
            st.subheader("🔍 Raw Output")
            st.text(answer)