Merge branch 'main' into feature/minio-rmq-integration

Author: agtk-nachov

DocsManager/app/core/config.py

@@ -55,13 +55,6 @@ def normalize_rabbitmq_host(cls, v: str) -> str:
             logger.warning("RABBITMQ_HOST is empty, using 'localhost' as default")
             return "localhost"
 
-        # Replace Docker service name with localhost
-        if v.strip() == "rabbitmq":
-            logger.warning(
-                "RABBITMQ_HOST='rabbitmq' detected. Changing to 'localhost' because app runs outside Docker"
-            )
-            return "localhost"
-        
         return v
 
     @model_validator(mode='after')

RAGManager/.env.example

@@ -1,9 +1,4 @@
-# PostgreSQL Configuration
-POSTGRES_USER=postgres
-POSTGRES_PASSWORD=postgres
-POSTGRES_DB=vectordb
-POSTGRES_HOST=localhost
-POSTGRES_PORT=5432
+DATABASE_URL=postgresql://postgres:postgres@postgres:5432/vectordb
 
 # RabbitMQ Configuration
 RABBITMQ_USER=guest
@@ -12,13 +7,24 @@ RABBITMQ_HOST=localhost
 RABBITMQ_PORT=5672
 RABBITMQ_MANAGEMENT_PORT=15672
 
+MINIO_ENDPOINT=http://minio:9000
+MINIO_ACCESS_KEY=minioadmin
+MINIO_SECRET_KEY=minioadmin
+MINIO_BUCKET=goland-bucket
+MINIO_FOLDER=rag-docs
+MINIO_USE_SSL=false
+
 # OpenAI Configuration
 OPENAI_API_KEY=your-openai-api-key-here
 
 # Chunking Configuration (if needed)
 CHUNK_SIZE=1000
 CHUNK_OVERLAP=200
 
+
+EMBEDDING_MODEL="text-embedding-3-small"
+EMBEDDING_DIMENSION=1536
+
 # =============================================================================
 # IMPORTANT NOTES
 # =============================================================================

RAGManager/app/services/chunking_service.py

@@ -1,4 +1,4 @@
-from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_text_splitters import RecursiveCharacterTextSplitter
 
 
 def split_documents(documents):

RAGManager/app/services/pipeline.py

@@ -3,7 +3,7 @@
 from langchain_core.documents import Document
 
 from app.core.config import settings
-from app.services.chunking_service import document_to_chunks
+from app.services.chunking_service import split_documents as document_to_chunks
 from app.services.embedding_service import chunks_to_embeddings
 from app.services.pdf_processor import pdf_to_document
 

RAGManager/pyproject.toml

@@ -3,7 +3,7 @@ name = "goland-ia"
 version = "0.1.0"
 description = "Add your description here"
 readme = "README.md"
-requires-python = ">=3.14"
+requires-python = ">=3.12,<3.13"
 dependencies = [
     "fastapi>=0.124.2",
     "ipython>=9.8.0",
@@ -17,7 +17,12 @@ dependencies = [
     "pydantic-settings>=2.0.0",
     "typing-extensions>=4.15.0",
     "uvicorn>=0.38.0",
-    "guardrails-ai>=0.6.2",
+    "guardrails-ai>=0.5.10",
+    "langchain>=1.2.0",
+    "langchain-community>=0.4.1",
+    "langchain-text-splitters>=1.1.0",
+    "pdfplumber>=0.11.8",
+    "minio>=7.2.20",
     "presidio-analyzer>=2.2.360",
     "presidio-anonymizer>=2.2.360",
 ]
@@ -82,4 +87,4 @@ indent-style = "space"
 skip-magic-trailing-comma = false
 
 # Automatically detect line ending
-line-ending = "auto"
+line-ending = "auto"

RAGManager/uv.lock

@@ -1,6 +1,53 @@
-version: '3.8'
-
 services:
+  docs-manager:
+    build:
+      context: ./DocsManager
+      dockerfile: Dockerfile
+    container_name: docs-manager
+    ports:
+      - "8000:8000"
+    env_file:
+      - .env
+      - ./DocsManager/.env
+    depends_on:
+      postgres:
+        condition: service_healthy
+      rabbitmq:
+        condition: service_healthy
+      minio:
+        condition: service_healthy
+    restart: unless-stopped
+    environment:
+      - PYTHONUNBUFFERED=1
+      - SERVICE_NAME=docs-manager
+      - SERVICE_ROLE=document-handler
+    networks:
+      - app-network
+
+  rag-manager:
+    build:
+      context: ./RAGManager
+      dockerfile: Dockerfile
+    container_name: rag-manager
+    ports:
+      - "8001:8000"
+    env_file:
+      - .env
+      - ./RAGManager/.env
+    depends_on:
+      postgres:
+        condition: service_healthy
+      rabbitmq:
+        condition: service_healthy
+      minio:
+        condition: service_healthy
+    restart: unless-stopped
+    environment:
+      - PYTHONUNBUFFERED=1
+      - SERVICE_NAME=rag-manager
+      - SERVICE_ROLE=document-processor
+    networks:
+      - app-network
   # PostgreSQL con pgvector
   postgres:
     build: