Upgrade the declarative pipeline for cleaner interface (#51)

This commit is contained in:
Nguyen Trung Duc (john)
2023-10-24 11:12:22 +07:00
committed by GitHub
parent aab982ddc4
commit 9035e25666
26 changed files with 365 additions and 169 deletions

View File

@@ -3,7 +3,7 @@ from pathlib import Path
from langchain.schema import Document as LangchainDocument
from llama_index.node_parser import SimpleNodeParser
from kotaemon.documents.base import Document, HaystackDocument
from kotaemon.documents.base import Document
from kotaemon.loaders import AutoReader
@@ -19,10 +19,6 @@ def test_pdf_reader():
assert isinstance(first_doc, Document)
assert first_doc.text.lower().replace(" ", "") == "dummypdffile"
# check conversion output
haystack_doc = first_doc.to_haystack_format()
assert isinstance(haystack_doc, HaystackDocument)
langchain_doc = first_doc.to_langchain_format()
assert isinstance(langchain_doc, LangchainDocument)