updated

app.py

@@ -48,6 +48,10 @@ import json
 # anywhere without needing to change configuration.  The ``chroma_db``
 # directory will be created automatically by the Chroma client if it does not
 # exist.
+import shutil
+
+# Remove any old unwritable Chroma DB path from previous versions
+shutil.rmtree("/app/chatbot/chroma_db", ignore_errors=True)
 CHATBOT_TXT_PATH = os.path.join(current_dir, 'chatbot', 'chatbot.txt')
 CHATBOT_DB_DIR = "/tmp/chroma_db"
 # API credentials for Groq.  These values mirror those in the standalone
@@ -170,8 +174,11 @@ def get_chatbot_response(query: str) -> str:
     # the application that might use OpenAI for different providers.
     openai.api_key = GROQ_API_KEY
     openai.api_base = "https://api.groq.com/openai/v1"
+    from openai import OpenAI
+
+    client = OpenAI(api_key=GROQ_API_KEY, base_url="https://api.groq.com/openai/v1")
 
-    completion = openai.ChatCompletion.create(
+    completion = client.chat.completions.create(
         model=GROQ_MODEL,
         messages=[
             {"role": "system", "content": system_prompt},
@@ -181,7 +188,8 @@ def get_chatbot_response(query: str) -> str:
         temperature=0.3,
     )
 
-    return completion['choices'][0]['message']['content'].strip()
+    return completion.choices[0].message["content"].strip()
+
 # Initialize Flask app
 app = Flask(
     __name__,

chatbot/chatbot.py

@@ -1,77 +0,0 @@
-# chatbot/chatbot.py
-
-from flask import Flask, request, jsonify
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from sentence_transformers import SentenceTransformer
-import chromadb
-from chromadb.config import Settings
-import openai
-import os
-
-# === CONFIG ===
-GROQ_API_KEY = "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"
-GROQ_MODEL = "llama3-8b-8192"
-CHATBOT_TXT_PATH = "./chatbot/chatbot.txt"
-
-# === Setup ===
-app = Flask(__name__)
-openai.api_key = GROQ_API_KEY
-openai.api_base = "https://api.groq.com/openai/v1"
-
-# === Load and split chatbot.txt ===
-text = open(CHATBOT_TXT_PATH, encoding="utf-8").read()
-splitter = RecursiveCharacterTextSplitter(chunk_size=300, chunk_overlap=100)
-docs = [doc.strip() for doc in splitter.split_text(text)]
-
-# === Embed and store in ChromaDB ===
-embedder = SentenceTransformer("all-MiniLM-L6-v2")
-embeddings = embedder.encode(docs, show_progress_bar=True, batch_size=32)
-
-client = chromadb.Client(Settings(persist_directory="./chatbot/chroma_db", anonymized_telemetry=False))
-collection = client.get_or_create_collection("chatbot")
-ids = [f"doc_{i}" for i in range(len(docs))]
-collection.add(documents=docs, embeddings=embeddings, ids=ids)
-
-# === Core logic ===
-def get_response(query: str) -> str:
-    query_embedding = embedder.encode([query])[0]
-    results = collection.query(query_embeddings=[query_embedding], n_results=3)
-    retrieved_docs = results['documents'][0]
-    context = "\n".join(retrieved_docs)
-
-    system_prompt = (
-        "You are a helpful assistant for the Codingo website. "
-        "Only answer questions that are directly relevant to the context provided. "
-        "If the user asks anything unrelated, politely refuse by saying: "
-        "\"I'm only trained to answer questions about the Codingo platform.\""
-    )
-
-    user_prompt = f"Context:\n{context}\n\nQuestion: {query}"
-
-    completion = openai.ChatCompletion.create(
-        model=GROQ_MODEL,
-        messages=[
-            {"role": "system", "content": system_prompt},
-            {"role": "user", "content": user_prompt},
-        ],
-        max_tokens=200,
-        temperature=0.3,
-    )
-
-    return completion['choices'][0]['message']['content'].strip()
-
-# === Flask route ===
-@app.route("/chat", methods=["POST"])
-def chat():
-    user_input = request.json.get("message", "").strip()
-    if not user_input:
-        return jsonify({"error": "Empty message"}), 400
-
-    try:
-        reply = get_response(user_input)
-        return jsonify({"response": reply})
-    except Exception as e:
-        return jsonify({"error": str(e)}), 500
-
-if __name__ == "__main__":
-    app.run(port=5001)