Update README

README.md

@@ -1,14 +1,8 @@
 # ElasticSearch Index
 
-*author: Jael*
-
-<br />
-
 ## Description
 
-The index operator index the given documents in ElasticSearch to get ready for retrieval.
-It accepts a single document in dictionary or a list of documents (dictionaries) as input.
-For each document, the index automatically generates a unique id.
+The index operator index the given documents in ElasticSearch to get ready for retrieval. It accepts a single document in dictionary or a list of documents (dictionaries) as input.
 To use this operator, you need to [set up ElasticSearch](https://www.elastic.co/guide/en/elasticsearch/reference/current/setup.html) in advance.
 
 <br />
@@ -18,15 +12,11 @@ To use this operator, you need to [set up ElasticSearch](https://www.elastic.co/
 Insert an example document into ElasticSearch with address of localhost:9200 and index of 'test_index'.
 
 ```python
-from datetime import datetime
 from towhee import pipe, ops, DataCollection
 
 
 example_doc = {
-    'title': 'Test Title',
-    'author': 'Towhee',
-    'content': 'This is an example.',
-    'timestamp': datetime.now()
+    'sentence': 'This is an example.',
     }
 
 es_insert = (
@@ -34,11 +24,12 @@ es_insert = (
         .map(('index_name', 'doc'), 'res', ops.elasticsearch.osschat_index(
             host='localhost', port=9200
         ))
+        .map('doc', 'doc', lambda x: str(x))
         .output('doc', 'res')
 )
 
-res = es_insert('test_index', example_doc) # OR: es_insert('test_index', [example_doc])
-DataCollection(res).show() # Optional: display output data
+res = es_insert('test_index_5', example_doc)
+DataCollection(res).show()
 ```
 
 <br />

es_index.py

@@ -25,9 +25,9 @@ class ESIndex(PyOperator):
         super().__init__()
         try:
             self.client = Elasticsearch(
-                f'https://{host}:{port}',
+                f'http://{host}:{port}' if not ca_certs else f'https://{host}:{port}',
                 ca_certs=ca_certs,
-                basic_auth=(user, password))
+                basic_auth=(user, password) if user and password else None)
             logger.info('Successfully connected to ElasticSearch client.')
         except Exception as e:
             logger.error('Failed to connect ElasticSearch client:\n', e)
@@ -37,9 +37,7 @@ class ESIndex(PyOperator):
     def __call__(self, index_name: str, doc: Union[dict, List[dict]]):
         # if index not exist, create with stop words analyzer to strengthen the search accuracy
         if not self.is_index_exist(index_name):
-            logger.info(f'index{index_name} not exists, will create the index with stopwords analyzer')
-            self.create_index_with_stopwords(index_name)
-
+            self.create_index(index_name)
         if isinstance(doc, dict):
             docs = [doc]
         else:
@@ -52,9 +50,9 @@ class ESIndex(PyOperator):
             {
                 '_op_type': 'index',
                 '_index': index_name,
-                '_source': docs[i] 
+                '_source': d
             }
-            for i in range(len(docs))
+            for d in docs
         ]
         res = elasticsearch.helpers.bulk(self.client, actions, refresh=True)
         return res
@@ -62,46 +60,25 @@ class ESIndex(PyOperator):
     def is_index_exist(self, index_name: str):
         return self.client.indices.exists(index=index_name)
 
-    def create_index_with_stopwords(self, index_name: str):
+    def create_index(self, index_name: str):
+        settings = {
+            "analysis": {"analyzer": {"default": {"type": "standard"}}},
+            "similarity": {
+                "custom_bm25": {
+                    "type": "BM25",
+                    "k1": 2.0,
+                    "b": 0.75,
+                }
+            },
+        }
         mappings = {
             "properties": {
-                "milvus_id": {
-                    "type": "long"
-                },
-                "paragraph": {
-                    "type": "text",
-                    "analyzer": "my_stop_analyzer",
-                    "fields": {
-                        "keyword": {
-                            "type": "keyword",
-                            "ignore_above": 256
-                        }
-                    }
-                },
-                "path": {
+                "sentence": {
                     "type": "text",
-                    "analyzer": "my_stop_analyzer",
-                    "fields": {
-                        "keyword": {
-                            "type": "keyword",
-                            "ignore_above": 256
-                        }
-                    }
+                    "similarity": "custom_bm25",  # Use the custom BM25 similarity
                 }
             }
         }
-        settings = {
-            "analysis": {
-                "analyzer": {
-                    "my_stop_analyzer": {
-                        "type": "stop",
-                        "stopwords_path": "stopwords/stopwords-en.txt"
-                    }
-                }
-            },
-            "number_of_shards": 3,
-            "number_of_replicas": 0
-        }
-        self.client.indices.create(index=index_name, mappings=mappings, settings=settings)
-        logger.info(f"created index{index_name}")
 
+        # Create the index with the specified settings and mappings
+        self.client.indices.create(index=index_name, mappings=mappings, settings=settings)