github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-08-30 17:29:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix typing in WebResearchRetriver (#10734)

Browse Source 
Hello @hwchase17 

**Issue**:
The class WebResearchRetriever accept only
RecursiveCharacterTextSplitter, but never uses a specification of this
class. I propose to change the type to TextSplitter. Then, the lint can
accept all subtypes.
This commit is contained in:
Philippe PRADOS 2023-09-18 17:17:10 +02:00 committed by GitHub
parent 8201cae770
commit 39c1c94272
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
libs/langchain/langchain/retrievers/web_research.py
View File

@ -16,7 +16,7 @@ from langchain.output_parsers.pydantic import PydanticOutputParser
from langchain.prompts import BasePromptTemplate, PromptTemplate
from langchain.pydantic_v1 import BaseModel, Field
from langchain.schema import BaseRetriever, Document
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.text_splitter import RecursiveCharacterTextSplitter, TextSplitter
from langchain.utilities import GoogleSearchAPIWrapper
from langchain.vectorstores.base import VectorStore
@ -75,7 +75,7 @@ class WebResearchRetriever(BaseRetriever):
llm_chain: LLMChain
search: GoogleSearchAPIWrapper = Field(..., description="Google Search API Wrapper")
num_search_results: int = Field(1, description="Number of pages per Google search")
text_splitter: RecursiveCharacterTextSplitter = Field(
text_splitter: TextSplitter = Field(
RecursiveCharacterTextSplitter(chunk_size=1500, chunk_overlap=50),
description="Text splitter for splitting web pages into chunks",
)