chore: Remove obsolete build and GUI files, and introduce a new Docker Compose setup for microservices architecture. This change streamlines the project structure by eliminating legacy scripts and integrating a PostgreSQL database service alongside extraction and cleaning services.

services/api_gateway/Dockerfile

@@ -0,0 +1,15 @@
+FROM python:3.11-slim
+
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    PYTHONPATH=/app
+
+WORKDIR /app
+
+COPY requirements.txt /app/requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY api /app/api
+
+EXPOSE 8000
+CMD ["uvicorn", "api.main:app", "--host", "0.0.0.0", "--port", "8000"]

services/api_gateway/README.md

@@ -0,0 +1,29 @@
+# IPSExtractor API Gateway
+
+Gateway HTTP opcional. Esta carpeta puede vivir como repo propio: solo depende
+de HTTP para hablar con `extraction` y `cleaning`; no importa codigo interno de
+esos servicios.
+
+## Estructura
+
+```text
+api/             Endpoints FastAPI y proxy HTTP
+requirements.txt
+Dockerfile
+```
+
+## Desarrollo local
+
+```bash
+pip install -r requirements.txt
+uvicorn api.main:app --host 0.0.0.0 --port 8000
+```
+
+## Endpoints principales
+
+- `GET /health`
+- `GET /models`
+- `GET /config`
+- `ANY /extraction/{path}`
+- `ANY /cleaning/{path}`
+

services/api_gateway/api/__init__.py

@@ -0,0 +1 @@
+"""API central opcional para enrutar a los microservicios."""

services/api_gateway/api/main.py

@@ -0,0 +1,110 @@
+"""Gateway HTTP sin compartir codigo interno de los microservicios."""
+from __future__ import annotations
+
+import os
+from typing import Any
+
+import httpx
+from fastapi import FastAPI, Request, Response
+
+
+EXTRACTION_URL = os.getenv("EXTRACTION_URL", "http://extraction:8001").rstrip("/")
+CLEANING_URL = os.getenv("CLEANING_URL", "http://cleaning:8002").rstrip("/")
+
+app = FastAPI(title="IPSExtractor API Gateway", version="1.0.0")
+
+
+@app.get("/health")
+async def health() -> dict[str, Any]:
+  async with httpx.AsyncClient(timeout=10.0) as client:
+    extraction = await _safe_health(client, EXTRACTION_URL)
+    cleaning = await _safe_health(client, CLEANING_URL)
+  return {
+    "status": "ok" if extraction["ok"] and cleaning["ok"] else "degraded",
+    "services": {
+      "extraction": extraction,
+      "cleaning": cleaning,
+    },
+  }
+
+
+@app.get("/models")
+async def models() -> Response:
+  return await _proxy("GET", f"{EXTRACTION_URL}/models")
+
+
+@app.get("/config")
+async def config() -> dict[str, Any]:
+  async with httpx.AsyncClient(timeout=15.0) as client:
+    extraction = await _safe_json(client, f"{EXTRACTION_URL}/config")
+    cleaning_rules = await _safe_json(client, f"{CLEANING_URL}/rules")
+  return {
+    "extraction": extraction,
+    "cleaning": {"rules": cleaning_rules},
+  }
+
+
+@app.api_route("/extraction/{path:path}", methods=["GET", "POST", "PUT", "PATCH", "DELETE"])
+async def extraction_proxy(path: str, request: Request) -> Response:
+  return await _proxy_request(request, f"{EXTRACTION_URL}/{path}")
+
+
+@app.api_route("/cleaning/{path:path}", methods=["GET", "POST", "PUT", "PATCH", "DELETE"])
+async def cleaning_proxy(path: str, request: Request) -> Response:
+  return await _proxy_request(request, f"{CLEANING_URL}/{path}")
+
+
+async def _safe_health(client: httpx.AsyncClient, base_url: str) -> dict[str, Any]:
+  try:
+    response = await client.get(f"{base_url}/health")
+    return {"ok": response.is_success, "status_code": response.status_code}
+  except Exception as exc:
+    return {"ok": False, "error": str(exc)}
+
+
+async def _safe_json(client: httpx.AsyncClient, url: str) -> Any:
+  try:
+    response = await client.get(url)
+    response.raise_for_status()
+    return response.json()
+  except Exception as exc:
+    return {"error": str(exc)}
+
+
+async def _proxy(method: str, url: str) -> Response:
+  async with httpx.AsyncClient(timeout=60.0) as client:
+    upstream = await client.request(method, url)
+  return _to_response(upstream)
+
+
+async def _proxy_request(request: Request, url: str) -> Response:
+  body = await request.body()
+  headers = {
+    key: value
+    for key, value in request.headers.items()
+    if key.lower() not in {"host", "content-length"}
+  }
+  async with httpx.AsyncClient(timeout=None) as client:
+    upstream = await client.request(
+      request.method,
+      url,
+      params=request.query_params,
+      content=body,
+      headers=headers,
+    )
+  return _to_response(upstream)
+
+
+def _to_response(upstream: httpx.Response) -> Response:
+  excluded = {"content-encoding", "transfer-encoding", "connection"}
+  headers = {
+    key: value
+    for key, value in upstream.headers.items()
+    if key.lower() not in excluded
+  }
+  return Response(
+    content=upstream.content,
+    status_code=upstream.status_code,
+    headers=headers,
+    media_type=upstream.headers.get("content-type"),
+  )

services/api_gateway/requirements.txt

@@ -0,0 +1,3 @@
+fastapi==0.115.6
+httpx==0.28.1
+uvicorn[standard]==0.32.1