elasticsearch-haystack 1.0.0__py3-none-any.whl → 2.0.0__py3-none-any.whl

{elasticsearch_haystack-1.0.0.dist-info → elasticsearch_haystack-2.0.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: elasticsearch-haystack
-Version: 1.0.0
+Version: 2.0.0
 Summary: Haystack 2.x Document Store for ElasticSearch
 Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/elasticsearch#readme
 Project-URL: Issues, https://github.com/deepset-ai/haystack-core-integrations/issues

{elasticsearch_haystack-1.0.0.dist-info → elasticsearch_haystack-2.0.0.dist-info}/RECORD

@@ -2,9 +2,9 @@ haystack_integrations/components/retrievers/elasticsearch/__init__.py,sha256=cSJ
 haystack_integrations/components/retrievers/elasticsearch/bm25_retriever.py,sha256=XA6UiNFb59CMM5LSoPmNDe3IzZ7ty7HViSaU2ZT4--w,5851
 haystack_integrations/components/retrievers/elasticsearch/embedding_retriever.py,sha256=ZL9kHi6tCzks1_GXoOIRVLcN4BWnaMqN6t-JcwdTfao,5992
 haystack_integrations/document_stores/elasticsearch/__init__.py,sha256=YTfu94dtVUBogbJFr1aJrKuaI6-Bw9VuHfPoyU7M8os,207
-haystack_integrations/document_stores/elasticsearch/document_store.py,sha256=-F6Ij1tZ6WfUyep49X6t0q40NIcEmwf1XhYY2BgFkZg,18788
-haystack_integrations/document_stores/elasticsearch/filters.py,sha256=L1tN7YCIDuNdhGrBQdPoqXFk37x__2-K038xZ6PRdNQ,9923
-elasticsearch_haystack-1.0.0.dist-info/METADATA,sha256=L4XxIMl6z2IQkNQ-7Pe3cXbzcsv5gmljEnZsTMolwPo,2168
-elasticsearch_haystack-1.0.0.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-elasticsearch_haystack-1.0.0.dist-info/licenses/LICENSE,sha256=_M2kulivnaiTHiW-5CRlZrPmH47tt04pBgAgeDvfYi4,11342
-elasticsearch_haystack-1.0.0.dist-info/RECORD,,
+haystack_integrations/document_stores/elasticsearch/document_store.py,sha256=lNHnzVm30dHdZr6jJtRHY212r5fN7a2w_PEUCdoseA4,19817
+haystack_integrations/document_stores/elasticsearch/filters.py,sha256=Umip-PP4uFjuWeB1JWkKhaKClQ0VpiykoDlDu99wIV0,9759
+elasticsearch_haystack-2.0.0.dist-info/METADATA,sha256=wTRyUYeJy0jvMOa9t0JtWHv105JE2awalXH7pmVSmyI,2168
+elasticsearch_haystack-2.0.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+elasticsearch_haystack-2.0.0.dist-info/licenses/LICENSE,sha256=_M2kulivnaiTHiW-5CRlZrPmH47tt04pBgAgeDvfYi4,11342
+elasticsearch_haystack-2.0.0.dist-info/RECORD,,

{elasticsearch_haystack-1.0.0.dist-info → elasticsearch_haystack-2.0.0.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: hatchling 1.25.0
+Generator: hatchling 1.27.0
 Root-Is-Purelib: true
 Tag: py3-none-any

haystack_integrations/document_stores/elasticsearch/document_store.py

@@ -105,9 +105,12 @@ class ElasticsearchDocumentStore:
     @property
     def client(self) -> Elasticsearch:
         if self._client is None:
+            headers = self._kwargs.pop("headers", {})
+            headers["user-agent"] = f"haystack-py-ds/{haystack_version}"
+
             client = Elasticsearch(
                 self._hosts,
-                headers={"user-agent": f"haystack-py-ds/{haystack_version}"},
+                headers=headers,
                 **self._kwargs,
             )
             # Check client connection, this will raise if not connected
@@ -255,6 +258,15 @@ class ElasticsearchDocumentStore:
         elasticsearch_actions = []
         for doc in documents:
             doc_dict = doc.to_dict()
+            if "dataframe" in doc_dict:
+                dataframe = doc_dict.pop("dataframe")
+                if dataframe:
+                    logger.warning(
+                        "Document %s has the `dataframe` field set,"
+                        "ElasticsearchDocumentStore no longer supports dataframes and this field will be ignored. "
+                        "The `dataframe` field will soon be removed from Haystack Document.",
+                        doc.id,
+                    )
             if "sparse_embedding" in doc_dict:
                 sparse_embedding = doc_dict.pop("sparse_embedding", None)
                 if sparse_embedding:
@@ -319,6 +331,15 @@ class ElasticsearchDocumentStore:
             data["metadata"]["highlighted"] = hit["highlight"]
         data["score"] = hit["_score"]
 
+        if "dataframe" in data:
+            dataframe = data.pop("dataframe")
+            if dataframe:
+                logger.warning(
+                    "Document %s has the `dataframe` field set,"
+                    "ElasticsearchDocumentStore no longer supports dataframes and this field will be ignored. "
+                    "The `dataframe` field will soon be removed from Haystack Document.",
+                    data["id"],
+                )
         return Document.from_dict(data)
 
     def delete_documents(self, document_ids: List[str]) -> None:

haystack_integrations/document_stores/elasticsearch/filters.py

@@ -5,7 +5,6 @@ from datetime import datetime
 from typing import Any, Dict, List
 
 from haystack.errors import FilterError
-from pandas import DataFrame
 
 
 def _normalize_filters(filters: Dict[str, Any]) -> Dict[str, Any]:
@@ -57,7 +56,7 @@ def _equal(field: str, value: Any) -> Dict[str, Any]:
                 }
             }
         }
-    if field in ["text", "dataframe"]:
+    if field == "text":
         # We want to fully match the text field.
         return {"match": {field: {"query": value, "minimum_should_match": "100%"}}}
     return {"term": {field: value}}
@@ -69,7 +68,7 @@ def _not_equal(field: str, value: Any) -> Dict[str, Any]:
 
     if isinstance(value, list):
         return {"bool": {"must_not": {"terms": {field: value}}}}
-    if field in ["text", "dataframe"]:
+    if field == "text":
         # We want to fully match the text field.
         return {"bool": {"must_not": {"match": {field: {"query": value, "minimum_should_match": "100%"}}}}}
 
@@ -92,7 +91,7 @@ def _greater_than(field: str, value: Any) -> Dict[str, Any]:
                 "Strings are only comparable if they are ISO formatted dates."
             )
             raise FilterError(msg) from exc
-    if type(value) in [list, DataFrame]:
+    if isinstance(value, list):
         msg = f"Filter value can't be of type {type(value)} using operators '>', '>=', '<', '<='"
         raise FilterError(msg)
     return {"range": {field: {"gt": value}}}
@@ -114,7 +113,7 @@ def _greater_than_equal(field: str, value: Any) -> Dict[str, Any]:
                 "Strings are only comparable if they are ISO formatted dates."
             )
             raise FilterError(msg) from exc
-    if type(value) in [list, DataFrame]:
+    if isinstance(value, list):
         msg = f"Filter value can't be of type {type(value)} using operators '>', '>=', '<', '<='"
         raise FilterError(msg)
     return {"range": {field: {"gte": value}}}
@@ -136,7 +135,7 @@ def _less_than(field: str, value: Any) -> Dict[str, Any]:
                 "Strings are only comparable if they are ISO formatted dates."
             )
             raise FilterError(msg) from exc
-    if type(value) in [list, DataFrame]:
+    if isinstance(value, list):
         msg = f"Filter value can't be of type {type(value)} using operators '>', '>=', '<', '<='"
         raise FilterError(msg)
     return {"range": {field: {"lt": value}}}
@@ -158,7 +157,7 @@ def _less_than_equal(field: str, value: Any) -> Dict[str, Any]:
                 "Strings are only comparable if they are ISO formatted dates."
             )
             raise FilterError(msg) from exc
-    if type(value) in [list, DataFrame]:
+    if isinstance(value, list):
         msg = f"Filter value can't be of type {type(value)} using operators '>', '>=', '<', '<='"
         raise FilterError(msg)
     return {"range": {field: {"lte": value}}}
@@ -212,8 +211,6 @@ def _parse_comparison_condition(condition: Dict[str, Any]) -> Dict[str, Any]:
         raise FilterError(msg)
     operator: str = condition["operator"]
     value: Any = condition["value"]
-    if isinstance(value, DataFrame):
-        value = value.to_json()
 
     return COMPARISON_OPERATORS[operator](field, value)