Updated

Dockerfile

@@ -1,46 +1,31 @@
-# ------------------------------
+# ----------------------
+# DevAssist AI Dockerfile
+# ----------------------
+
 # Base image
-# ------------------------------
 FROM python:3.10-slim
 
-# ------------------------------
-# Create a non-root user
-# ------------------------------
-RUN useradd -m appuser
+# Set working directory
 WORKDIR /app
-USER appuser
-
-# ------------------------------
-# Install system dependencies
-# ------------------------------
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    git \
-    curl \
-    && rm -rf /var/lib/apt/lists/*
-
-# ------------------------------
-# Copy requirements and install
-# ------------------------------
-COPY --chown=appuser:appuser requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
 
-# ------------------------------
-# Create cache & DB folders (writable by appuser)
-# ------------------------------
+# Create directories for caches and Chroma DB (writable by default user)
 RUN mkdir -p /app/huggingface_cache /app/Dev_Assist_SME_Builder_DB
 
-# ------------------------------
-# Copy app source code
-# ------------------------------
-COPY --chown=appuser:appuser . .
+# Copy requirements first (to leverage Docker cache)
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy all project files
+COPY . .
 
-# ------------------------------
 # Expose FastAPI port
-# ------------------------------
 EXPOSE 7860
 
-# ------------------------------
-# CMD to run FastAPI
-# ------------------------------
-CMD ["python", "-m", "uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]
+# Set environment variables for cache directories (HuggingFace & Chroma)
+ENV HF_HOME=/app/huggingface_cache
+ENV CHROMA_DB_DIR=/app/Dev_Assist_SME_Builder_DB
+
+# Default command to start FastAPI via Uvicorn
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

smebuilder_vector.py

@@ -1,21 +1,59 @@
-# Base image
-FROM python:3.10-slim
+# smebuilder_vector.py
 
-# Set working directory
-WORKDIR /app
+import os
+import pandas as pd
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_chroma import Chroma
+from langchain_core.documents import Document
 
-# Copy and install Python dependencies
-COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
+# ----------------- 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
 
-# Copy project files
-COPY . .
+# ----------------- LOAD DATASET -----------------
+if not os.path.exists(DATASET_PATH):
+    raise FileNotFoundError(f"Dataset file not found: {DATASET_PATH}")
 
-# Make folders writable for HuggingFace / Chroma
-RUN mkdir -p /app/huggingface_cache /app/Dev_Assist_SME_Builder_DB
+df = pd.read_csv(DATASET_PATH)
 
-# Expose FastAPI port
-EXPOSE 7860
+# ----------------- EMBEDDINGS -----------------
+embeddings = HuggingFaceEmbeddings(
+    model_name=EMBEDDING_MODEL,
+    model_kwargs={"cache_dir": HF_CACHE}  # pass writable cache
+)
 
-# Run as default user
-CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]
+# ----------------- 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})