github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-04 20:46:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

infra: rm unused # noqa violations (#22049)

Browse Source 
Updating #21137
This commit is contained in:
Bagatur
2024-05-22 15:21:08 -07:00
committed by GitHub
parent 45ed5f3f51
commit 50186da0a1
149 changed files with 212 additions and 214 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
templates/rag-redis/ingest.py
View File

@@ -17,7 +17,7 @@ def ingest_documents():
data_path = "data/"
doc = [os.path.join(data_path, file) for file in os.listdir(data_path)][0]
print("Parsing 10k filing doc for NIKE", doc) # noqa: T201
print("Parsing 10k filing doc for NIKE", doc)
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=1500, chunk_overlap=100, add_start_index=True
@@ -25,7 +25,7 @@ def ingest_documents():
loader = UnstructuredFileLoader(doc, mode="single", strategy="fast")
chunks = loader.load_and_split(text_splitter)
print("Done preprocessing. Created", len(chunks), "chunks of the original pdf") # noqa: T201
print("Done preprocessing. Created", len(chunks), "chunks of the original pdf")
# Create vectorstore
embedder = HuggingFaceEmbeddings(model_name=EMBED_MODEL)