Bagatur/vectara nit (#9140)

Co-authored-by: Ofer Mendelevitch <ofer@vectara.com>

docs/extras/integrations/providers/vectara/index.mdx

@@ -63,7 +63,7 @@ results = vectara.similarity_score("what is LangChain?")
 - `k`: number of results to return (defaults to 5)
 - `lambda_val`: the [lexical matching](https://docs.vectara.com/docs/api-reference/search-apis/lexical-matching) factor for hybrid search (defaults to 0.025)
 - `filter`: a [filter](https://docs.vectara.com/docs/common-use-cases/filtering-by-metadata/filter-overview) to apply to the results (default None)
-- `n_sentence_context`: number of sentences to include before/after the actual matching segment when returning results. This defaults to 0 so as to return the exact text segment that matches, but can be used with other values e.g. 2 or 3 to return adjacent text segments.
+- `n_sentence_context`: number of sentences to include before/after the actual matching segment when returning results. This defaults to 2.
 
 The results are returned as a list of relevant documents, and a relevance score of each document.
 

libs/langchain/langchain/vectorstores/vectara.py

@@ -245,7 +245,7 @@ class Vectara(VectorStore):
         k: int = 5,
         lambda_val: float = 0.025,
         filter: Optional[str] = None,
-        n_sentence_context: int = 0,
+        n_sentence_context: int = 2,
         **kwargs: Any,
     ) -> List[Tuple[Document, float]]:
         """Return Vectara documents most similar to query, along with scores.
@@ -259,7 +259,7 @@ class Vectara(VectorStore):
                 https://docs.vectara.com/docs/search-apis/sql/filter-overview
                 for more details.
             n_sentence_context: number of sentences before/after the matching segment
-                to add
+                to add, defaults to 2
 
         Returns:
             List of Documents most similar to the query and score for each.
@@ -328,7 +328,7 @@ class Vectara(VectorStore):
         k: int = 5,
         lambda_val: float = 0.025,
         filter: Optional[str] = None,
-        n_sentence_context: int = 0,
+        n_sentence_context: int = 2,
         **kwargs: Any,
     ) -> List[Document]:
         """Return Vectara documents most similar to query, along with scores.
@@ -341,7 +341,7 @@ class Vectara(VectorStore):
                 https://docs.vectara.com/docs/search-apis/sql/filter-overview for more
                 details.
             n_sentence_context: number of sentences before/after the matching segment
-                to add
+                to add, defaults to 2
 
         Returns:
             List of Documents most similar to the query
@@ -427,7 +427,7 @@ class VectaraRetriever(VectorStoreRetriever):
             "lambda_val": 0.025,
             "k": 5,
             "filter": "",
-            "n_sentence_context": "0",
+            "n_sentence_context": "2",
         }
     )
     """Search params.

libs/langchain/tests/integration_tests/vectorstores/test_vectara.py

@@ -86,7 +86,6 @@ def test_vectara_from_files() -> None:
         n_sentence_context=0,
         filter="doc.test_num = 2",
     )
-    print(output)
     assert output[0].page_content == (
         "By the commonly adopted machine learning tradition "
         "(e.g., Chapter 28 in Murphy, 2012; Deng and Li, 2013), it may be natural "
@@ -94,3 +93,24 @@ def test_vectara_from_files() -> None:
         "(e.g., DNNs) and deep probabilistic generative models (e.g., DBN, Deep "
         "Boltzmann Machine (DBM))."
     )
+
+    # finally do a similarity search to see if all works okay
+    output = docsearch.similarity_search(
+        "By the commonly adopted machine learning tradition",
+        k=1,
+        n_sentence_context=1,
+        filter="doc.test_num = 2",
+    )
+    print(output[0].page_content)
+    assert output[0].page_content == (
+        """\
+Note the use of “hybrid” in 3) above is different from that used sometimes in the literature, \
+which for example refers to the hybrid systems for speech recognition feeding the output probabilities of a neural network into an HMM \
+(Bengio et al., 1991; Bourlard and Morgan, 1993; Morgan, 2012). \
+By the commonly adopted machine learning tradition (e.g., Chapter 28 in Murphy, 2012; Deng and Li, 2013), \
+it may be natural to just classify deep learning techniques into deep discriminative models (e.g., DNNs) \
+and deep probabilistic generative models (e.g., DBN, Deep Boltzmann Machine (DBM)). \
+This classification scheme, however, misses a key insight gained in deep learning research about how generative \
+models can greatly improve the training of DNNs and other deep discriminative models via better regularization.\
+"""  # noqa: E501
+    )