github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-03 20:16:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Bagatur/vectara nit (#9140)

Browse Source 
Co-authored-by: Ofer Mendelevitch <ofer@vectara.com>
This commit is contained in:
Bagatur
2023-08-11 15:32:03 -07:00
committed by GitHub
parent 9b64932e55
commit 45741bcc1b
3 changed files with 27 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
libs/langchain/langchain/vectorstores/vectara.py
View File

@@ -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.

22
libs/langchain/tests/integration_tests/vectorstores/test_vectara.py
View File

@@ -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
)