github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-24 23:54:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix MultiQueryRetriever breaking Embeddings with empty lines (#21093)

Browse Source 
Fix MultiQueryRetriever breaking Embeddings with empty lines

```
[chain/end] [1:chain:ConversationalRetrievalChain > 2:retriever:Retriever > 3:retriever:Retriever > 4:chain:LLMChain] [2.03s] Exiting Chain run with output:
[outputs]
> /workspaces/Sfeir/sncf/metabot-backend/.venv/lib/python3.11/site-packages/langchain/retrievers/multi_query.py(116)_aget_relevant_documents()
-> if self.include_original:
(Pdb) queries
['## Alternative questions for "Hello, tell me about phones?":', '', '1. **What are the latest trends in smartphone technology?** (Focuses on recent advancements)', '2. **How has the mobile phone industry evolved over the years?** (Historical perspective)', '3. **What are the different types of phones available in the market, and which one is best for me?** (Categorization and recommendation)']
```

Example of failure on VertexAIEmbeddings

```
grpc._channel._InactiveRpcError: <_InactiveRpcError of RPC that terminated with:
	status = StatusCode.INVALID_ARGUMENT
	details = "The text content is empty."
	debug_error_string = "UNKNOWN:Error received from peer ipv4:142.250.184.234:443 {created_time:"2024-04-30T09:57:45.625698408+00:00", grpc_status:3, grpc_message:"The text content is empty."}"
```

Fixes: #15959

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
This commit is contained in:
Shikanime Deva 2024-07-19 19:13:12 +02:00 committed by GitHub
parent 5affbada61
commit 9c3da11910
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 16 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/docs/how_to/MultiQueryRetriever.ipynb
View File

@ -153,7 +153,7 @@
"\n", "\n",
" def parse(self, text: str) -> List[str]:\n", " def parse(self, text: str) -> List[str]:\n",
" lines = text.strip().split(\"\\n\")\n", " lines = text.strip().split(\"\\n\")\n",
" return lines\n", " return list(filter(None, lines)) # Remove empty lines\n",
"\n", "\n",
"\n", "\n",
"output_parser = LineListOutputParser()\n", "output_parser = LineListOutputParser()\n",

2
libs/langchain/langchain/retrievers/multi_query.py
View File

@ -24,7 +24,7 @@ class LineListOutputParser(BaseOutputParser[List[str]]):
def parse(self, text: str) -> List[str]: def parse(self, text: str) -> List[str]:
lines = text.strip().split("\n") lines = text.strip().split("\n")
return lines return list(filter(None, lines)) # Remove empty lines
# Default prompt # Default prompt

15
libs/langchain/tests/unit_tests/retrievers/test_multi_query.py
View File

@ -3,7 +3,7 @@ from typing import List
import pytest as pytest import pytest as pytest
from langchain_core.documents import Document from langchain_core.documents import Document
from langchain.retrievers.multi_query import _unique_documents from langchain.retrievers.multi_query import LineListOutputParser, _unique_documents
@pytest.mark.parametrize( @pytest.mark.parametrize(
@ -38,3 +38,16 @@ from langchain.retrievers.multi_query import _unique_documents
) )
def test__unique_documents(documents: List[Document], expected: List[Document]) -> None: def test__unique_documents(documents: List[Document], expected: List[Document]) -> None:
assert _unique_documents(documents) == expected assert _unique_documents(documents) == expected
@pytest.mark.parametrize(
"text,expected",
[
("foo\nbar\nbaz", ["foo", "bar", "baz"]),
("foo\nbar\nbaz\n", ["foo", "bar", "baz"]),
("foo\n\nbar", ["foo", "bar"]),
],
)
def test_line_list_output_parser(text: str, expected: List[str]) -> None:
parser = LineListOutputParser()
assert parser.parse(text) == expected