community[patch]: Correct the calling to collection_name in qdrant (#16920)

## Description

In #16608, the calling `collection_name` was wrong.
I made a fix for it. 
Sorry for the inconvenience!

## Issue

https://github.com/langchain-ai/langchain/issues/16962

## Dependencies

N/A



<!-- Thank you for contributing to LangChain!

Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.

Replace this entire comment with:
  - **Description:** a description of the change, 
  - **Issue:** the issue # it fixes if applicable,
  - **Dependencies:** any dependencies required for this change,
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!

Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` from the root
of the package you've modified to check this locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/

If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->

---------

Co-authored-by: Kumar Shivendu <kshivendu1@gmail.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>

libs/community/langchain_community/retrievers/qdrant_sparse_vector_retriever.py

@@ -120,7 +120,10 @@ class QdrantSparseVectorRetriever(BaseRetriever):
         )
         return [
             Qdrant._document_from_scored_point(
-                point, self.content_payload_key, self.metadata_payload_key
+                point,
+                self.collection_name,
+                self.content_payload_key,
+                self.metadata_payload_key,
             )
             for point in results
         ]

libs/community/langchain_community/vectorstores/qdrant.py

@@ -620,7 +620,10 @@ class Qdrant(VectorStore):
         return [
             (
                 self._document_from_scored_point(
-                    result, self.content_payload_key, self.metadata_payload_key
+                    result,
+                    self.collection_name,
+                    self.content_payload_key,
+                    self.metadata_payload_key,
                 ),
                 result.score,
             )
@@ -713,7 +716,10 @@ class Qdrant(VectorStore):
         return [
             (
                 self._document_from_scored_point(
-                    result, self.content_payload_key, self.metadata_payload_key
+                    result,
+                    self.collection_name,
+                    self.content_payload_key,
+                    self.metadata_payload_key,
                 ),
                 result.score,
             )
@@ -1051,7 +1057,10 @@ class Qdrant(VectorStore):
         return [
             (
                 self._document_from_scored_point(
-                    results[i], self.content_payload_key, self.metadata_payload_key
+                    results[i],
+                    self.collection_name,
+                    self.content_payload_key,
+                    self.metadata_payload_key,
                 ),
                 results[i].score,
             )
@@ -1123,7 +1132,10 @@ class Qdrant(VectorStore):
         return [
             (
                 self._document_from_scored_point(
-                    results[i], self.content_payload_key, self.metadata_payload_key
+                    results[i],
+                    self.collection_name,
+                    self.content_payload_key,
+                    self.metadata_payload_key,
                 ),
                 results[i].score,
             )
@@ -1938,12 +1950,13 @@ class Qdrant(VectorStore):
     def _document_from_scored_point(
         cls,
         scored_point: Any,
+        collection_name: str,
         content_payload_key: str,
         metadata_payload_key: str,
     ) -> Document:
         metadata = scored_point.payload.get(metadata_payload_key) or {}
         metadata["_id"] = scored_point.id
-        metadata["_collection_name"] = scored_point.collection_name
+        metadata["_collection_name"] = collection_name
         return Document(
             page_content=scored_point.payload.get(content_payload_key),
             metadata=metadata,

libs/community/tests/integration_tests/vectorstores/qdrant/async_api/test_from_texts.py

@@ -12,7 +12,10 @@ from tests.integration_tests.vectorstores.fake_embeddings import (
 from tests.integration_tests.vectorstores.qdrant.async_api.fixtures import (
     qdrant_locations,
 )
-from tests.integration_tests.vectorstores.qdrant.common import qdrant_is_not_running
+from tests.integration_tests.vectorstores.qdrant.common import (
+    assert_documents_equals,
+    qdrant_is_not_running,
+)
 
 
 @pytest.mark.parametrize("qdrant_location", qdrant_locations())
@@ -245,4 +248,6 @@ async def test_qdrant_from_texts_stores_metadatas(
         location=qdrant_location,
     )
     output = await docsearch.asimilarity_search("foo", k=1)
-    assert output == [Document(page_content="foo", metadata={"page": 0})]
+    assert_documents_equals(
+        output, [Document(page_content="foo", metadata={"page": 0})]
+    )

libs/community/tests/integration_tests/vectorstores/qdrant/async_api/test_max_marginal_relevance.py

@@ -10,6 +10,7 @@ from tests.integration_tests.vectorstores.fake_embeddings import (
 from tests.integration_tests.vectorstores.qdrant.async_api.fixtures import (
     qdrant_locations,
 )
+from tests.integration_tests.vectorstores.qdrant.common import assert_documents_equals
 
 
 @pytest.mark.parametrize("batch_size", [1, 64])
@@ -41,7 +42,10 @@ async def test_qdrant_max_marginal_relevance_search(
     output = await docsearch.amax_marginal_relevance_search(
         "foo", k=2, fetch_k=3, lambda_mult=0.0
     )
-    assert output == [
-        Document(page_content="foo", metadata={"page": 0}),
-        Document(page_content="baz", metadata={"page": 2}),
-    ]
+    assert_documents_equals(
+        output,
+        [
+            Document(page_content="foo", metadata={"page": 0}),
+            Document(page_content="baz", metadata={"page": 2}),
+        ],
+    )

libs/community/tests/integration_tests/vectorstores/qdrant/async_api/test_similarity_search.py

@@ -11,6 +11,7 @@ from tests.integration_tests.vectorstores.fake_embeddings import (
 from tests.integration_tests.vectorstores.qdrant.async_api.fixtures import (
     qdrant_locations,
 )
+from tests.integration_tests.vectorstores.qdrant.common import assert_documents_equals
 
 
 @pytest.mark.parametrize("batch_size", [1, 64])
@@ -37,7 +38,7 @@ async def test_qdrant_similarity_search(
         location=qdrant_location,
     )
     output = await docsearch.asimilarity_search("foo", k=1)
-    assert output == [Document(page_content="foo")]
+    assert_documents_equals(output, [Document(page_content="foo")])
 
 
 @pytest.mark.parametrize("batch_size", [1, 64])
@@ -65,7 +66,7 @@ async def test_qdrant_similarity_search_by_vector(
     )
     embeddings = ConsistentFakeEmbeddings().embed_query("foo")
     output = await docsearch.asimilarity_search_by_vector(embeddings, k=1)
-    assert output == [Document(page_content="foo")]
+    assert_documents_equals(output, [Document(page_content="foo")])
 
 
 @pytest.mark.parametrize("batch_size", [1, 64])
@@ -95,7 +96,7 @@ async def test_qdrant_similarity_search_with_score_by_vector(
     output = await docsearch.asimilarity_search_with_score_by_vector(embeddings, k=1)
     assert len(output) == 1
     document, score = output[0]
-    assert document == Document(page_content="foo")
+    assert_documents_equals([document], [Document(page_content="foo")])
     assert score >= 0
 
 
@@ -123,12 +124,15 @@ async def test_qdrant_similarity_search_filters(
     output = await docsearch.asimilarity_search(
         "foo", k=1, filter={"page": 1, "metadata": {"page": 2, "pages": [3]}}
     )
-    assert output == [
-        Document(
-            page_content="bar",
-            metadata={"page": 1, "metadata": {"page": 2, "pages": [3, -1]}},
-        )
-    ]
+    assert_documents_equals(
+        output,
+        [
+            Document(
+                page_content="bar",
+                metadata={"page": 1, "metadata": {"page": 2, "pages": [3, -1]}},
+            )
+        ],
+    )
 
 
 @pytest.mark.parametrize("vector_name", [None, "my-vector"])
@@ -262,12 +266,15 @@ async def test_qdrant_similarity_search_filters_with_qdrant_filters(
         ]
     )
     output = await docsearch.asimilarity_search("foo", k=1, filter=qdrant_filter)
-    assert output == [
-        Document(
-            page_content="bar",
-            metadata={"page": 1, "details": {"page": 2, "pages": [3, -1]}},
-        )
-    ]
+    assert_documents_equals(
+        output,
+        [
+            Document(
+                page_content="bar",
+                metadata={"page": 1, "details": {"page": 2, "pages": [3, -1]}},
+            )
+        ],
+    )
 
 
 @pytest.mark.parametrize("batch_size", [1, 64])

libs/community/tests/integration_tests/vectorstores/qdrant/common.py

@@ -1,3 +1,8 @@
+from typing import List
+
+from langchain_core.documents import Document
+
+
 def qdrant_is_not_running() -> bool:
     """Check if Qdrant is not running."""
     import requests
@@ -8,3 +13,18 @@ def qdrant_is_not_running() -> bool:
         return response_json.get("title") != "qdrant - vector search engine"
     except (requests.exceptions.ConnectionError, requests.exceptions.Timeout):
         return True
+
+
+def assert_documents_equals(actual: List[Document], expected: List[Document]):
+    assert len(actual) == len(expected)
+
+    for actual_doc, expected_doc in zip(actual, expected):
+        assert actual_doc.page_content == expected_doc.page_content
+
+        assert "_id" in actual_doc.metadata
+        assert "_collection_name" in actual_doc.metadata
+
+        actual_doc.metadata.pop("_id")
+        actual_doc.metadata.pop("_collection_name")
+
+        assert actual_doc.metadata == expected_doc.metadata

libs/community/tests/integration_tests/vectorstores/qdrant/test_add_texts.py

@@ -8,6 +8,7 @@ from langchain_community.vectorstores import Qdrant
 from tests.integration_tests.vectorstores.fake_embeddings import (
     ConsistentFakeEmbeddings,
 )
+from tests.integration_tests.vectorstores.qdrant.common import assert_documents_equals
 
 
 @pytest.mark.parametrize("batch_size", [1, 64])
@@ -33,7 +34,7 @@ def test_qdrant_add_documents_extends_existing_collection(
     # ConsistentFakeEmbeddings return the same query embedding as the first document
     # embedding computed in `embedding.embed_documents`. Thus, "foo" embedding is the
     # same as "foobar" embedding
-    assert output == [Document(page_content="foobar")]
+    assert_documents_equals(output, [Document(page_content="foobar")])
 
 
 @pytest.mark.parametrize("batch_size", [1, 64])

libs/community/tests/integration_tests/vectorstores/qdrant/test_from_texts.py

@@ -10,7 +10,10 @@ from langchain_community.vectorstores.qdrant import QdrantException
 from tests.integration_tests.vectorstores.fake_embeddings import (
     ConsistentFakeEmbeddings,
 )
-from tests.integration_tests.vectorstores.qdrant.common import qdrant_is_not_running
+from tests.integration_tests.vectorstores.qdrant.common import (
+    assert_documents_equals,
+    qdrant_is_not_running,
+)
 
 
 def test_qdrant_from_texts_stores_duplicated_texts() -> None:
@@ -257,7 +260,9 @@ def test_qdrant_from_texts_stores_metadatas(
         batch_size=batch_size,
     )
     output = docsearch.similarity_search("foo", k=1)
-    assert output == [Document(page_content="foo", metadata={"page": 0})]
+    assert_documents_equals(
+        output, [Document(page_content="foo", metadata={"page": 0})]
+    )
 
 
 @pytest.mark.skipif(qdrant_is_not_running(), reason="Qdrant is not running")

libs/community/tests/integration_tests/vectorstores/qdrant/test_max_marginal_relevance.py

@@ -7,6 +7,7 @@ from langchain_community.vectorstores import Qdrant
 from tests.integration_tests.vectorstores.fake_embeddings import (
     ConsistentFakeEmbeddings,
 )
+from tests.integration_tests.vectorstores.qdrant.common import assert_documents_equals
 
 
 @pytest.mark.parametrize("batch_size", [1, 64])
@@ -49,14 +50,18 @@ def test_qdrant_max_marginal_relevance_search(
     output = docsearch.max_marginal_relevance_search(
         "foo", k=2, fetch_k=3, lambda_mult=0.0
     )
-    assert output == [
-        Document(page_content="foo", metadata={"page": 0}),
-        Document(page_content="baz", metadata={"page": 2}),
-    ]
+    assert_documents_equals(
+        output,
+        [
+            Document(page_content="foo", metadata={"page": 0}),
+            Document(page_content="baz", metadata={"page": 2}),
+        ],
+    )
 
     output = docsearch.max_marginal_relevance_search(
         "foo", k=2, fetch_k=3, lambda_mult=0.0, filter=filter
     )
-    assert output == [
-        Document(page_content="baz", metadata={"page": 2}),
-    ]
+    assert_documents_equals(
+        output,
+        [Document(page_content="baz", metadata={"page": 2})],
+    )

libs/community/tests/integration_tests/vectorstores/qdrant/test_similarity_search.py

@@ -8,6 +8,7 @@ from langchain_community.vectorstores import Qdrant
 from tests.integration_tests.vectorstores.fake_embeddings import (
     ConsistentFakeEmbeddings,
 )
+from tests.integration_tests.vectorstores.qdrant.common import assert_documents_equals
 
 
 @pytest.mark.parametrize("batch_size", [1, 64])
@@ -32,7 +33,7 @@ def test_qdrant_similarity_search(
         vector_name=vector_name,
     )
     output = docsearch.similarity_search("foo", k=1)
-    assert output == [Document(page_content="foo")]
+    assert_documents_equals(actual=output, expected=[Document(page_content="foo")])
 
 
 @pytest.mark.parametrize("batch_size", [1, 64])
@@ -58,7 +59,7 @@ def test_qdrant_similarity_search_by_vector(
     )
     embeddings = ConsistentFakeEmbeddings().embed_query("foo")
     output = docsearch.similarity_search_by_vector(embeddings, k=1)
-    assert output == [Document(page_content="foo")]
+    assert_documents_equals(output, [Document(page_content="foo")])
 
 
 @pytest.mark.parametrize("batch_size", [1, 64])
@@ -86,7 +87,7 @@ def test_qdrant_similarity_search_with_score_by_vector(
     output = docsearch.similarity_search_with_score_by_vector(embeddings, k=1)
     assert len(output) == 1
     document, score = output[0]
-    assert document == Document(page_content="foo")
+    assert_documents_equals(actual=[document], expected=[Document(page_content="foo")])
     assert score >= 0
 
 
@@ -113,12 +114,16 @@ def test_qdrant_similarity_search_filters(
     output = docsearch.similarity_search(
         "foo", k=1, filter={"page": 1, "metadata": {"page": 2, "pages": [3]}}
     )
-    assert output == [
-        Document(
-            page_content="bar",
-            metadata={"page": 1, "metadata": {"page": 2, "pages": [3, -1]}},
-        )
-    ]
+
+    assert_documents_equals(
+        actual=output,
+        expected=[
+            Document(
+                page_content="bar",
+                metadata={"page": 1, "metadata": {"page": 2, "pages": [3, -1]}},
+            )
+        ],
+    )
 
 
 @pytest.mark.parametrize("vector_name", [None, "my-vector"])
@@ -240,12 +245,15 @@ def test_qdrant_similarity_search_filters_with_qdrant_filters(
         ]
     )
     output = docsearch.similarity_search("foo", k=1, filter=qdrant_filter)
-    assert output == [
-        Document(
-            page_content="bar",
-            metadata={"page": 1, "details": {"page": 2, "pages": [3, -1]}},
-        )
-    ]
+    assert_documents_equals(
+        actual=output,
+        expected=[
+            Document(
+                page_content="bar",
+                metadata={"page": 1, "details": {"page": 2, "pages": [3, -1]}},
+            )
+        ],
+    )
 
 
 @pytest.mark.parametrize("batch_size", [1, 64])