ci pipeline (#1)

.github/workflows/ci.yml

@@ -48,10 +48,10 @@ jobs:
         run: uv sync --group dev
 
       - name: ruff — check
-        run: uv run ruff check .
+        run: uv run ruff check app data evaluation frontend pipelines scripts vector_store
 
       - name: ruff — format
-        run: uv run ruff format --check .
+        run: uv run ruff format --check app data evaluation frontend pipelines scripts vector_store
 
   test:
     name: Test

README.md

@@ -3,14 +3,14 @@
 <h1 align="center">Global Retail Intelligence Engine
 <br>
 <!-- Version Badge - update on release (must match CHANGELOG.md) -->
-<a href="https://github.com/kokou-egbewatt/re-llm_engineering/tags">
-    <img src="https://img.shields.io/github/v/tag/kokou-egbewatt/re-llm_engineering?label=version" alt="Version">
+<a href="https://github.com/kokou-egbewatt/retail-intelligence/tags">
+    <img src="https://img.shields.io/github/v/tag/kokou-egbewatt/retail-intelligence?label=version" alt="Version">
 </a>
 </h1>
 <p align="center">
   <i>Advanced RAG pipeline for product search, regional pricing, policies, and secure querying across 11 markets.</i><br><br>
-  <a href="https://github.com/kokou-egbewatt/re-llm_engineering/actions/workflows/ci.yml">
-    <img src="https://github.com/kokou-egbewatt/re-llm_engineering/actions/workflows/ci.yml/badge.svg" alt="CI"/>
+  <a href="https://github.com/kokou-egbewatt/retail-intelligence/actions/workflows/ci.yml">
+    <img src="https://github.com/kokou-egbewatt/retail-intelligence/actions/workflows/ci.yml/badge.svg" alt="CI"/>
   </a>
   <img src="https://img.shields.io/badge/Python-3.11+-3776AB?style=flat-square&logo=python&logoColor=white" alt="Python"/>
   <img src="https://img.shields.io/badge/FastAPI-009688?style=flat-square&logo=fastapi&logoColor=white" alt="FastAPI"/>

app/api/chat.py

@@ -2,7 +2,7 @@
 Chat API: POST /chat - accepts query and optional country, returns RAG response.
 """
 
-from fastapi import APIRouter, HTTPException
+from fastapi import APIRouter
 from pydantic import BaseModel, Field
 
 from app.rag.pipeline import run_rag

app/main.py

@@ -6,15 +6,16 @@
 
 from dotenv import load_dotenv
 
-# Load .env from project root (parent of app/)
-_env_path = Path(__file__).resolve().parent.parent / ".env"
-load_dotenv(_env_path)
-
 from fastapi import FastAPI
 from fastapi.middleware.cors import CORSMiddleware
 
 from app.api.chat import router as chat_router
 
+# Load .env from project root (parent of app/)
+_env_path = Path(__file__).resolve().parent.parent / ".env"
+load_dotenv(_env_path)
+
+
 app = FastAPI(
     title="Global Retail Intelligence Engine",
     description="RAG API for product search, regional pricing, and policy answers.",

app/rag/hybrid_search.py

@@ -152,7 +152,7 @@ def search(
         bm25_scores = self._bm25.get_scores(tokenized_query)
         order_bm25 = np.argsort(bm25_scores)[::-1][:vector_k]
         indices_bm25 = order_bm25.tolist()
-        scores_bm25_list = bm25_scores.tolist()
+        _ = bm25_scores.tolist()  # scores_bm25_list
 
         # Reciprocal rank fusion: score = 1/(rank_vec) + 1/(rank_bm25)
         rank_vec = {idx: r for r, idx in enumerate(indices_vec, 1)}

app/rag/pipeline.py

@@ -7,7 +7,7 @@
 import os
 import re
 from dataclasses import dataclass
-from typing import Any, List, Optional
+from typing import List, Optional
 
 from app.guardrails.prompt_injection import detect_prompt_injection
 from app.guardrails.security_filter import check_restricted_data
@@ -83,7 +83,7 @@ def _merge_retrieval_results(
     for lst in result_lists:
         for doc in lst:
             doc_id = doc.get(id_key) or id(doc)
-            score = doc.get("score", 0.0)
+            _ = doc.get("score", 0.0)  # score
             if doc_id not in by_id or (doc.get("score") or 0) > (
                 by_id[doc_id].get("score") or 0
             ):

scripts/run_indexing.py

@@ -5,20 +5,19 @@
 import sys
 from pathlib import Path
 
+from pipelines.indexing.build_vector_index import main as index_main
+from pipelines.ingestion.clean_data import main as clean_main
+
 # Add project root
 project_root = Path(__file__).resolve().parent.parent
 sys.path.insert(0, str(project_root))
 
-from pipelines.indexing.build_vector_index import main as index_main
-from pipelines.ingestion.clean_data import main as clean_main
-
 
 def main():
     # Ingest Task 1 xlsx if present (adds GH-K-001, UK-W-202 Policy, NL-L-5042, etc.)
     task_xlsx = project_root / "Task 1_ Global Retail Intelligence Engine Data.xlsx"
     if task_xlsx.exists():
-        from pipelines.ingestion.ingest_task_data import \
-            main as ingest_task_main
+        from pipelines.ingestion.ingest_task_data import main as ingest_task_main
 
         ingest_task_main()
         print("Re-running clean to merge task data...")

scripts/run_retrieval.py

@@ -7,15 +7,15 @@
 import sys
 from pathlib import Path
 
+from app.rag.hybrid_search import HybridRetriever
+
 # Quiet HuggingFace / sentence-transformers logs when running as CLI
 os.environ.setdefault("TRANSFORMERS_VERBOSITY", "error")
 os.environ.setdefault("HF_HUB_DISABLE_PROGRESS_BARS", "1")
 
 project_root = Path(__file__).resolve().parent.parent
 sys.path.insert(0, str(project_root))
 
-from app.rag.hybrid_search import HybridRetriever
-
 
 def main():
     query = "How much does the Solar Inverter cost?"