Update version to v0.0.74 (#825)

.github/workflows/ci.yml

@@ -24,9 +24,7 @@ jobs:
         run: poetry install --all-extras
       - name: Lint with ruff
         run: make lint
-      - name: Test with pytest
+      - name: Run tests and generate coverage report
-        run: make test
-      - name: Generate coverage report
         run: make coverage
       - name: Upload coverage reports to Codecov
         uses: codecov/codecov-action@v3
@@ -34,4 +32,3 @@ jobs:
           file: coverage.xml
         env:
           CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-

embedchain/data_formatter/data_formatter.py

@@ -6,11 +6,11 @@ from embedchain.chunkers.json import JSONChunker
 from embedchain.chunkers.mdx import MdxChunker
 from embedchain.chunkers.notion import NotionChunker
 from embedchain.chunkers.pdf_file import PdfFileChunker
-from embedchain.chunkers.unstructured_file import UnstructuredFileChunker
 from embedchain.chunkers.qna_pair import QnaPairChunker
 from embedchain.chunkers.sitemap import SitemapChunker
 from embedchain.chunkers.table import TableChunker
 from embedchain.chunkers.text import TextChunker
+from embedchain.chunkers.unstructured_file import UnstructuredFileChunker
 from embedchain.chunkers.web_page import WebPageChunker
 from embedchain.chunkers.xml import XmlChunker
 from embedchain.chunkers.youtube_video import YoutubeVideoChunker
@@ -28,10 +28,10 @@ from embedchain.loaders.local_text import LocalTextLoader
 from embedchain.loaders.mdx import MdxLoader
 from embedchain.loaders.pdf_file import PdfFileLoader
 from embedchain.loaders.sitemap import SitemapLoader
+from embedchain.loaders.unstructured_file import UnstructuredLoader
 from embedchain.loaders.web_page import WebPageLoader
 from embedchain.loaders.xml import XmlLoader
 from embedchain.loaders.youtube_video import YoutubeVideoLoader
-from embedchain.loaders.unstructured_file import UnstructuredLoader
 from embedchain.models.data_type import DataType
 
 

embedchain/loaders/json.py

@@ -1,6 +1,7 @@
 import hashlib
 
-from langchain.document_loaders.json_loader import JSONLoader as LcJSONLoader
+from langchain.document_loaders.json_loader import \
+    JSONLoader as LangchainJSONLoader
 
 from embedchain.loaders.base_loader import BaseLoader
 
@@ -13,7 +14,7 @@ class JSONLoader(BaseLoader):
         """Load a json file. Each data point is a key value pair."""
         data = []
         data_content = []
-        loader = LcJSONLoader(content, text_content=False, jq_schema=langchain_json_jq_schema)
+        loader = LangchainJSONLoader(content, text_content=False, jq_schema=langchain_json_jq_schema)
         docs = loader.load()
         for doc in docs:
             meta_data = doc.metadata

embedchain/models/data_type.py

@@ -25,7 +25,7 @@ class IndirectDataType(Enum):
     CSV = "csv"
     MDX = "mdx"
     IMAGES = "images"
-    UNSTRUCTURED = 'unstructured'
+    UNSTRUCTURED = "unstructured"
     JSON = "json"
 
 

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "embedchain"
-version = "0.0.73"
+version = "0.0.74"
 description = "Data platform for LLMs - Load, index, retrieve and sync any unstructured data"
 authors = ["Taranjeet Singh, Deshraj Yadav"]
 license = "Apache License"

tests/chunkers/test_chunkers.py

@@ -1,5 +1,6 @@
 from embedchain.chunkers.docs_site import DocsSiteChunker
 from embedchain.chunkers.docx_file import DocxFileChunker
+from embedchain.chunkers.json import JSONChunker
 from embedchain.chunkers.mdx import MdxChunker
 from embedchain.chunkers.notion import NotionChunker
 from embedchain.chunkers.pdf_file import PdfFileChunker
@@ -10,7 +11,6 @@ from embedchain.chunkers.text import TextChunker
 from embedchain.chunkers.web_page import WebPageChunker
 from embedchain.chunkers.xml import XmlChunker
 from embedchain.chunkers.youtube_video import YoutubeVideoChunker
-from embedchain.chunkers.json import JSONChunker
 from embedchain.config.add_config import ChunkerConfig
 
 chunker_config = ChunkerConfig(chunk_size=500, chunk_overlap=0, length_function=len)

tests/loaders/test_json.py

@@ -2,7 +2,8 @@ import hashlib
 from unittest.mock import patch
 
 from langchain.docstore.document import Document
-from langchain.document_loaders.json_loader import JSONLoader as LcJSONLoader
+from langchain.document_loaders.json_loader import \
+    JSONLoader as LangchainJSONLoader
 
 from embedchain.loaders.json import JSONLoader
 
@@ -12,10 +13,10 @@ def test_load_data():
         Document(page_content="content1", metadata={"seq_num": 1}),
         Document(page_content="content2", metadata={"seq_num": 2}),
     ]
-    with patch.object(LcJSONLoader, "load", return_value=mock_document):
+    with patch.object(LangchainJSONLoader, "load", return_value=mock_document):
         content = "temp.json"
 
-        result = JsonLoader.load_data(content)
+        result = JSONLoader.load_data(content)
 
         assert "doc_id" in result
         assert "data" in result