Updated

smebuilder_vector.py

@@ -1,59 +1,36 @@
-# smebuilder_vector.py
-
-import os
-import pandas as pd
-from langchain_huggingface import HuggingFaceEmbeddings
-from langchain_chroma import Chroma
-from langchain_core.documents import Document
-
-# ----------------- CONFIG -----------------
-DATASET_PATH = "sme_builder_dataset.csv"
-DB_LOCATION = "/app/Dev_Assist_SME_Builder_DB"  # absolute path for container
-COLLECTION_NAME = "landing_page_generation_examples"
-EMBEDDING_MODEL = "intfloat/e5-base-v2"
-HF_CACHE = "/app/huggingface_cache"  # writable cache folder
-
-# ----------------- LOAD DATASET -----------------
-if not os.path.exists(DATASET_PATH):
-    raise FileNotFoundError(f"Dataset file not found: {DATASET_PATH}")
-
-df = pd.read_csv(DATASET_PATH)
-
-# ----------------- EMBEDDINGS -----------------
-embeddings = HuggingFaceEmbeddings(
-    model_name=EMBEDDING_MODEL,
-    model_kwargs={"cache_dir": HF_CACHE}  # pass writable cache
-)
-
-# ----------------- CHECK VECTOR STORE -----------------
-add_documents = not os.path.exists(DB_LOCATION)
-
-# ----------------- CREATE DOCUMENTS -----------------
-documents, ids = [], []
-if add_documents:
-    for i, row in df.iterrows():
-        prompt = row.get("prompt", "")
-        html_code = row.get("html_code", "")
-        css_code = row.get("css_code", "")
-        js_code = row.get("js_code", "")
-        sector = row.get("sector", "")
-
-        page_content = " ".join(
-            [str(prompt), str(html_code), str(css_code), str(js_code), str(sector)]
-        ).strip()
-
-        documents.append(Document(page_content=page_content, id=str(i)))
-        ids.append(str(i))
-
-# ----------------- VECTOR STORE -----------------
-vector_store = Chroma(
-    collection_name=COLLECTION_NAME,
-    persist_directory=DB_LOCATION,
-    embedding_function=embeddings,
-)
-
-if add_documents and documents:
-    vector_store.add_documents(documents=documents, ids=ids)
-
-# ----------------- RETRIEVER -----------------
-retriever = vector_store.as_retriever(search_kwargs={"k": 20})
+# Use lightweight Python image
+FROM python:3.10-slim
+
+# ----------------- SYSTEM DEPENDENCIES -----------------
+# Install as root (default user)
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    git \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# ----------------- CREATE NON-ROOT USER -----------------
+RUN useradd -m appuser
+
+# Set working directory
+WORKDIR /app
+
+# ----------------- COPY AND INSTALL PYTHON DEPENDENCIES -----------------
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# ----------------- COPY PROJECT FILES -----------------
+COPY . .
+
+# Make cache folders writable for appuser
+RUN mkdir -p /app/huggingface_cache /app/Dev_Assist_SME_Builder_DB \
+    && chown -R appuser:appuser /app/huggingface_cache /app/Dev_Assist_SME_Builder_DB /app
+
+# Switch to non-root user
+USER appuser
+
+# Expose FastAPI default port
+EXPOSE 7860
+
+# Command to run FastAPI with Uvicorn
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]