Update app.py

app.py

@@ -1,8 +1,8 @@
 import streamlit as st
 import pandas as pd
-import os
-import openai
 import numpy as np
+import os
+import requests
 import json
 import re
 
@@ -13,13 +13,18 @@ st.set_page_config(page_title="CSV-Backed AI Agent", layout="wide")
 st.title("CSV-Backed AI Agent")
 st.image("./nadi-lok-image.png")
 
-# — Load your OpenAI key
-openai.api_key = os.getenv("OPENAI_API_KEY")
-if not openai.api_key:
+# — 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()
 
-# — Sidebar CSV upload
+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")
 
@@ -27,7 +32,7 @@ if uploaded_file:
     try:
         df = pd.read_csv(uploaded_file)
         st.sidebar.success("File uploaded successfully!")
-        st.sidebar.write("Preview:")
+        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}")
@@ -40,17 +45,24 @@ if df is not None:
 
     @st.cache_data(show_spinner=False)
     def build_row_embeddings(df: pd.DataFrame):
-        # Serialize each row to a compact JSON string
-        texts = df.apply(lambda row: row.to_json(), axis=1).tolist()
+        # 1) Convert each row to a compact JSON string
+        texts = df.apply(lambda r: r.to_json(), axis=1).tolist()
 
-        # Batch‐call embeddings
-        all_embs = []
+        # 2) Batch‐call the embeddings endpoint
+        embeddings = []
         for i in range(0, len(texts), 100):
             batch = texts[i : i + 100]
-            resp = openai.Embedding.create(model="text-embedding-ada-002", input=batch)
-            all_embs.extend([d["embedding"] for d in resp["data"]])
-
-        return np.array(all_embs), texts
+            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)
 
@@ -69,18 +81,26 @@ if st.button("Run Agent"):
         st.error("Please enter a prompt.")
     else:
         # 1) Embed the prompt
-        q_resp = openai.Embedding.create(model="text-embedding-ada-002", input=[prompt])
-        q_emb = np.array(q_resp["data"][0]["embedding"])
+        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
-        row_norms = np.linalg.norm(embeddings, axis=1)
+        norms = np.linalg.norm(embeddings, axis=1)
         q_norm = np.linalg.norm(q_emb)
-        sims = embeddings.dot(q_emb) / (row_norms * q_norm + 1e-8)
-        # 3) Pick top K rows (e.g. 5)
+        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 messages
+        # 4) Build the chat messages
         system_msg = {
             "role": "system",
             "content": (
@@ -94,16 +114,22 @@ if st.button("Run Agent"):
         }
         user_msg = {"role": "user", "content": prompt}
 
-        # 5) Call ChatCompletion
-        chat = openai.ChatCompletion.create(
-            model="gpt-3.5-turbo",
-            messages=[system_msg, memory_msg, user_msg],
-            temperature=0,
-            max_tokens=1500,
+        # 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,
         )
-        answer = chat.choices[0].message.content
+        chat_resp.raise_for_status()
+        answer = chat_resp.json()["choices"][0]["message"]["content"]
 
-        # 6) Extract JSON
+        # 6) Extract the JSON payload
         txt = re.sub(r"```(?:json)?", "", answer).strip()
         start = txt.find("{")
         end = txt.rfind("}") + 1
@@ -115,7 +141,7 @@ if st.button("Run Agent"):
             except json.JSONDecodeError:
                 parsed = None
 
-        # 7) Display
+        # 7) Display results
         if parsed is not None:
             st.subheader("✅ JSON Output")
             st.json(parsed)