chore: Fix linter errors

Author: hinxcode

.flake8

@@ -0,0 +1,17 @@
+[flake8]
+max-line-length = 88
+extend-ignore = E203, E501
+exclude =
+    .git,
+    __pycache__,
+    venv,
+    .venv,
+    env,
+    .env,
+    build,
+    dist,
+    node_modules,
+    .pytest_cache,
+    .mypy_cache
+max-complexity = 10
+

scripts/create_loc_assets.py

@@ -6,15 +6,17 @@
 in the same way as we do in our public demo at https://digital-collections-explorer.com/
 """
 
+import base64
+import json
+
 import pandas as pd
 import torch
-import json
-import base64
 
-ORIGINAL_INDEX_PATH = 'input/beto_idx.pt'
-CSV_PATH = 'input/merged_files.csv'
-FINAL_METADATA_PATH = 'output/metadata.json'
-FINAL_INDEX_PATH = 'output/item_ids.pt'
+ORIGINAL_INDEX_PATH = "input/beto_idx.pt"
+CSV_PATH = "input/merged_files.csv"
+FINAL_METADATA_PATH = "output/metadata.json"
+FINAL_INDEX_PATH = "output/item_ids.pt"
+
 
 def generate_assets():
     # --- 1. Load the original beto_idx.pt file ---
@@ -24,9 +26,11 @@ def generate_assets():
 
     # --- 2. Build a lookup table from merged_files.csv ---
     df = pd.read_csv(CSV_PATH)
-    df.dropna(subset=['p1_item_id', 'file_url'], inplace=True)
-    df['iiif_id'] = df['file_url'].apply(lambda url: url.split('/')[5] if isinstance(url, str) else None)
-    df.dropna(subset=['iiif_id'], inplace=True)
+    df.dropna(subset=["p1_item_id", "file_url"], inplace=True)
+    df["iiif_id"] = df["file_url"].apply(
+        lambda url: url.split("/")[5] if isinstance(url, str) else None
+    )
+    df.dropna(subset=["iiif_id"], inplace=True)
     iiif_to_p1_lookup = pd.Series(df.p1_item_id.values, index=df.iiif_id).to_dict()
 
     # --- 3. Generate new index and metadata ---
@@ -36,15 +40,19 @@ def generate_assets():
     for image_url in original_idx:
         # a. Extract iiif_id
         try:
-            iiif_id = image_url.split('/')[5]
+            iiif_id = image_url.split("/")[5]
         except IndexError:
-            b64_key = base64.urlsafe_b64encode(f"ERROR_PARSING_{len(final_beto_idx)}".encode('utf-8')).decode('utf-8')
+            b64_key = base64.urlsafe_b64encode(
+                f"ERROR_PARSING_{len(final_beto_idx)}".encode("utf-8")
+            ).decode("utf-8")
             final_beto_idx.append(b64_key)
-            final_metadata[b64_key] = {'error': f'Could not parse iiif_id from URL: {image_url}'}
+            final_metadata[b64_key] = {
+                "error": f"Could not parse iiif_id from URL: {image_url}"
+            }
             continue
 
         # b. Generate Base64 key
-        b64_key = base64.urlsafe_b64encode(iiif_id.encode('utf-8')).decode('utf-8')
+        b64_key = base64.urlsafe_b64encode(iiif_id.encode("utf-8")).decode("utf-8")
 
         # c. Append key to the new index
         final_beto_idx.append(b64_key)
@@ -55,26 +63,31 @@ def generate_assets():
         # e. Assemble the new metadata object
         url_base = f"https://tile.loc.gov/image-services/iiif/{iiif_id}"
         paths = {
-            'original': f"{url_base}/full/pct:100/0/default.jpg",
-            'processed': f"{url_base}/full/2000,/0/default.jpg",
-            'thumbnail': f"{url_base}/full/400,/0/default.jpg"
+            "original": f"{url_base}/full/pct:100/0/default.jpg",
+            "processed": f"{url_base}/full/2000,/0/default.jpg",
+            "thumbnail": f"{url_base}/full/400,/0/default.jpg",
         }
         final_metadata[b64_key] = {
-            'type': 'image',
-            'iiif_id': iiif_id,
-            'url': p1_item_id,
-            'paths': paths
+            "type": "image",
+            "iiif_id": iiif_id,
+            "url": p1_item_id,
+            "paths": paths,
         }
 
     # --- 4. Final Save and Validation ---
-    with open(FINAL_METADATA_PATH, 'w') as f:
+    with open(FINAL_METADATA_PATH, "w") as f:
         json.dump(final_metadata, f, indent=4)
-    print(f"Successfully saved {FINAL_METADATA_PATH} with {len(final_metadata)} entries.")
+    print(
+        f"Successfully saved {FINAL_METADATA_PATH} with {len(final_metadata)} entries."
+    )
 
     torch.save(final_beto_idx, FINAL_INDEX_PATH)
     print(f"Successfully saved {FINAL_INDEX_PATH} with {len(final_beto_idx)} entries.")
 
-    assert len(original_idx) == len(final_beto_idx), "CRITICAL: Final index length does not match original!"
+    assert len(original_idx) == len(
+        final_beto_idx
+    ), "CRITICAL: Final index length does not match original!"
+
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     generate_assets()

src/backend/api/routes/embeddings.py

@@ -1,11 +1,13 @@
-from fastapi import APIRouter
 import logging
 
+from fastapi import APIRouter
+
 from ...services.embedding_service import embedding_service
 
 logger = logging.getLogger(__name__)
 router = APIRouter(prefix="/api/embeddings", tags=["embeddings"])
 
+
 @router.get("/count")
 async def get_total_embeddings():
     """Return the total number of embeddings."""

src/backend/api/routes/images.py

@@ -1,67 +1,89 @@
+from pathlib import Path
+
 from fastapi import APIRouter, HTTPException, Query
 from fastapi.responses import FileResponse
-from pathlib import Path
+
 from src.backend.services.embedding_service import embedding_service
 
 router = APIRouter(tags=["images"])
 
+
 @router.get("/images/{id}")
 async def get_image_by_id(
-    id: str,
-    size: str = Query("full", description="Image size: 'thumbnail' or 'full'")
+    id: str, size: str = Query("full", description="Image size: 'thumbnail' or 'full'")
 ):
     """
     Serve an image based on its ID
-    
+
     Args:
         id: The document ID
         size: Size of the image to return
     """
     doc = embedding_service.get_document_by_id(id)
-    
+
     if not doc:
         raise HTTPException(status_code=404, detail=f"Document with ID {id} not found")
-    
-    if size == "thumbnail" and "metadata" in doc and "paths" in doc["metadata"] and "thumbnail" in doc["metadata"]["paths"]:
+
+    if (
+        size == "thumbnail"
+        and "metadata" in doc
+        and "paths" in doc["metadata"]
+        and "thumbnail" in doc["metadata"]["paths"]
+    ):
         path_str = doc["metadata"]["paths"]["thumbnail"]
-    elif "metadata" in doc and "paths" in doc["metadata"] and "processed" in doc["metadata"]["paths"]:
+    elif (
+        "metadata" in doc
+        and "paths" in doc["metadata"]
+        and "processed" in doc["metadata"]["paths"]
+    ):
         path_str = doc["metadata"]["paths"]["processed"]
     else:
-        raise HTTPException(status_code=404, detail="Image path not found in document metadata")
-    
+        raise HTTPException(
+            status_code=404, detail="Image path not found in document metadata"
+        )
+
     path = Path(path_str)
-    
+
     if not path.exists():
         raise HTTPException(status_code=404, detail=f"Image not found at path: {path}")
-    
+
     return FileResponse(path)
 
+
 @router.get("/static/{id}")
 async def get_original_document(id: str):
     """
     Serve the original document file
-    
+
     Args:
         id: The document ID
     """
     doc = embedding_service.get_document_by_id(id)
 
     if not doc:
         raise HTTPException(status_code=404, detail=f"Document with ID {id} not found")
-    
-    if "metadata" in doc and "paths" in doc["metadata"] and "original" in doc["metadata"]["paths"]:
+
+    if (
+        "metadata" in doc
+        and "paths" in doc["metadata"]
+        and "original" in doc["metadata"]["paths"]
+    ):
         path_str = doc["metadata"]["paths"]["original"]
     else:
-        raise HTTPException(status_code=404, detail="Original file path not found in document metadata")
-    
+        raise HTTPException(
+            status_code=404, detail="Original file path not found in document metadata"
+        )
+
     path = Path(path_str)
-    
+
     if not path.exists():
-        raise HTTPException(status_code=404, detail=f"Original file not found at path: {path}")
-    
+        raise HTTPException(
+            status_code=404, detail=f"Original file not found at path: {path}"
+        )
+
     filename = path.name
     return FileResponse(
-        path, 
+        path,
         filename=filename,
-        headers={"Content-Disposition": f"attachment; filename={filename}"}
+        headers={"Content-Disposition": f"attachment; filename={filename}"},
     )

src/backend/api/routes/search.py

@@ -1,44 +1,48 @@
-from fastapi import APIRouter, File, Form, UploadFile, Query
-from PIL import Image
-from io import BytesIO
 import logging
+from io import BytesIO
+
+from fastapi import APIRouter, File, Form, Query, UploadFile
+from PIL import Image
 
-from ...services.embedding_service import embedding_service
-from ...services.clip_service import clip_service
 from ...models.schemas import SearchResponse, SearchResult
+from ...services.clip_service import clip_service
+from ...services.embedding_service import embedding_service
 
 logger = logging.getLogger(__name__)
 router = APIRouter(prefix="/api/search", tags=["search"])
 
+
 @router.get("/text", response_model=SearchResponse)
 async def search_by_text(
-    query: str, 
+    query: str,
     limit: int = Query(30, description="Number of results per page"),
-    page: int = Query(1, description="Page number for pagination")
+    page: int = Query(1, description="Page number for pagination"),
 ):
     """Search for similar content using text query."""
     offset = (page - 1) * limit
-    
+
     try:
         if not embedding_service.is_loaded:
             embedding_service.load_embeddings()
-        
+
         text_embedding = clip_service.encode_text(query)
         logit_scale = clip_service.model.logit_scale.exp().item()
-        raw_results = embedding_service.search(text_embedding, logit_scale=logit_scale, limit=limit, offset=offset)
-        
+        raw_results = embedding_service.search(
+            text_embedding, logit_scale=logit_scale, limit=limit, offset=offset
+        )
+
         search_results = [
             SearchResult(
-                id=result["id"],
-                score=result["score"],
-                metadata=result["metadata"]
-            ) for result in raw_results
+                id=result["id"], score=result["score"], metadata=result["metadata"]
+            )
+            for result in raw_results
         ]
         return SearchResponse(results=search_results)
     except Exception as e:
         logger.error(f"Error in text search: {str(e)}")
         return SearchResponse(results=[])
 
+
 @router.post("/image", response_model=SearchResponse)
 async def search_by_image(
     image: UploadFile = File(...),
@@ -47,19 +51,20 @@ async def search_by_image(
 ):
     """Search for similar content using an uploaded image."""
     offset = (page - 1) * limit
-    
+
     try:
         image_data = await image.read()
-        image = Image.open(BytesIO(image_data)).convert('RGB')
+        image = Image.open(BytesIO(image_data)).convert("RGB")
         image_embedding = clip_service.encode_image(image)
-        raw_results = embedding_service.search(image_embedding, limit=limit, offset=offset)
-        
+        raw_results = embedding_service.search(
+            image_embedding, limit=limit, offset=offset
+        )
+
         search_results = [
             SearchResult(
-                id=result["id"],
-                score=result["score"],
-                metadata=result["metadata"]
-            ) for result in raw_results
+                id=result["id"], score=result["score"], metadata=result["metadata"]
+            )
+            for result in raw_results
         ]
         return SearchResponse(results=search_results)
     except Exception as e: