fixing reformatted files

Author: andreluiz1987

supporting-blog-content/building-a-recipe-search-with-elasticsearch/elasticsearch_connection.py

@@ -8,8 +8,7 @@ def __init__(self, config_file="config.yml"):
         with open(config_file, "r") as f:
             config = yaml.safe_load(f)
             self.client = Elasticsearch(
-                cloud_id=config["cloud_id"],
-                api_key=config["api_key"]
+                cloud_id=config["cloud_id"], api_key=config["api_key"]
             )
 
     def get_client(self):
@@ -21,5 +20,6 @@ def get_async_client(self):
             self.client = AsyncElasticsearch(
                 cloud_id=config["cloud_id"],
                 api_key=config["api_key"],
-                request_timeout=240)
-        return self.client;
+                request_timeout=240,
+            )
+        return self.client

supporting-blog-content/building-a-recipe-search-with-elasticsearch/infra.py

@@ -17,10 +17,10 @@ def create_index_embedding():
                 "unit": {"type": "keyword"},
                 "description_embedding": {
                     "type": "semantic_text",
-                    "inference_id": "elser_embeddings"
-                }
+                    "inference_id": "elser_embeddings",
+                },
             }
-        }
+        },
     )
     print(response)
 
@@ -31,8 +31,9 @@ def create_inference():
         task_type="sparse_embedding",
         body={
             "service": "elser",
-            "service_settings": {"num_allocations": 1, "num_threads": 1}
-        })
+            "service_settings": {"num_allocations": 1, "num_threads": 1},
+        },
+    )
     print(response)
 
 

supporting-blog-content/building-a-recipe-search-with-elasticsearch/infra_lexical_index.py

@@ -14,9 +14,9 @@ def create_index():
                 "category": {"type": "keyword"},
                 "brand": {"type": "keyword"},
                 "price": {"type": "float"},
-                "unit": {"type": "keyword"}
+                "unit": {"type": "keyword"},
             }
-        }
+        },
     )
     print(response)
 

supporting-blog-content/building-a-recipe-search-with-elasticsearch/ingestion.py

@@ -9,7 +9,7 @@
 
 
 def partition_list(lst, chunk_size):
-    return [lst[i:i + chunk_size] for i in range(0, len(lst), chunk_size)]
+    return [lst[i : i + chunk_size] for i in range(0, len(lst), chunk_size)]
 
 
 async def index_data():
@@ -34,7 +34,9 @@ async def index_data():
 
 async def async_bulk_indexing(client, documents):
     success, failed = await helpers.async_bulk(client, documents)
-    print(f"Successfully indexed {success} documents. Failed to index {failed} documents.")
+    print(
+        f"Successfully indexed {success} documents. Failed to index {failed} documents."
+    )
 
 
 async def main():

supporting-blog-content/building-a-recipe-search-with-elasticsearch/ingestion_lexical_index.py

@@ -9,7 +9,7 @@
 
 
 def partition_list(lst, chunk_size):
-    return [lst[i:i + chunk_size] for i in range(0, len(lst), chunk_size)]
+    return [lst[i : i + chunk_size] for i in range(0, len(lst), chunk_size)]
 
 
 async def index_data():
@@ -34,7 +34,9 @@ async def index_data():
 
 async def async_bulk_indexing(client, documents):
     success, failed = await helpers.async_bulk(client, documents)
-    print(f"Successfully indexed {success} documents. Failed to index {failed} documents.")
+    print(
+        f"Successfully indexed {success} documents. Failed to index {failed} documents."
+    )
 
 
 async def main():

supporting-blog-content/building-a-recipe-search-with-elasticsearch/search.py

@@ -22,24 +22,21 @@ def search_semantic(term):
         index="grocery-catalog-elser",
         size=size,
         source_excludes="description_embedding",
-        query={
-            "semantic": {
-                "field": "description_embedding",
-                "query": term
-
-            }
-        })
+        query={"semantic": {"field": "description_embedding", "query": term}},
+    )
 
     for hit in response["hits"]["hits"]:
         score = hit["_score"]
         name = format_text(hit["_source"]["name"], line_length=10)
         description = hit["_source"]["description"]
         formatted_description = format_text(description)
-        result.append({
-            "score": score,
-            "name": name,
-            "description": formatted_description,
-        })
+        result.append(
+            {
+                "score": score,
+                "name": name,
+                "description": formatted_description,
+            }
+        )
     return result
 
 
@@ -49,38 +46,49 @@ def search_lexical(term):
         index="grocery-catalog-elser",
         size=size,
         source_excludes="description_embedding",
-        query={
-            "multi_match": {
-                "query": term,
-                "fields": [
-                    "name",
-                    "description"]
-            }
-        }
+        query={"multi_match": {"query": term, "fields": ["name", "description"]}},
     )
 
     for hit in response["hits"]["hits"]:
         score = hit["_score"]
         name = format_text(hit["_source"]["name"], line_length=10)
         description = hit["_source"]["description"]
-        result.append({
-            "score": score,
-            "name": name,
-            "description": description,
-        })
+        result.append(
+            {
+                "score": score,
+                "name": name,
+                "description": description,
+            }
+        )
     return result
 
 
 if __name__ == "__main__":
     rs1 = search_semantic(term)
     rs2 = search_lexical(term)
 
-    df1 = pd.DataFrame(rs1)[["name", "score"]] if rs1 else pd.DataFrame(columns=["name", "score"])
-    df2 = pd.DataFrame(rs2)[["name", "score"]] if rs2 else pd.DataFrame(columns=["name", "score"])
-    df1 = pd.DataFrame(rs1)[["name", "score"]] if rs1 else pd.DataFrame(columns=["name", "score"])
+    df1 = (
+        pd.DataFrame(rs1)[["name", "score"]]
+        if rs1
+        else pd.DataFrame(columns=["name", "score"])
+    )
+    df2 = (
+        pd.DataFrame(rs2)[["name", "score"]]
+        if rs2
+        else pd.DataFrame(columns=["name", "score"])
+    )
+    df1 = (
+        pd.DataFrame(rs1)[["name", "score"]]
+        if rs1
+        else pd.DataFrame(columns=["name", "score"])
+    )
     df1["Search Type"] = "Semantic"
 
-    df2 = pd.DataFrame(rs2)[["name", "score"]] if rs2 else pd.DataFrame(columns(["name", "score"]))
+    df2 = (
+        pd.DataFrame(rs2)[["name", "score"]]
+        if rs2
+        else pd.DataFrame(columns(["name", "score"]))
+    )
     df2["Search Type"] = "Lexical"
 
     tabela = pd.concat([df1, df2], axis=0).reset_index(drop=True)