Merge pull request #466 from baumandm/feat/epub-support

feat: Add epub support
This commit is contained in:
Timothy Jaeryang Baek 2024-01-22 23:12:46 -08:00 committed by GitHub
commit 7054f02891
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 37 additions and 11 deletions

View file

@ -45,6 +45,13 @@ COPY ./backend/requirements.txt ./requirements.txt
RUN pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir RUN pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir
RUN pip3 install -r requirements.txt --no-cache-dir RUN pip3 install -r requirements.txt --no-cache-dir
# Install pandoc
# RUN python -c "import pypandoc; pypandoc.download_pandoc()"
RUN apt-get update \
&& apt-get install -y pandoc \
&& rm -rf /var/lib/apt/lists/*
# RUN python -c "from sentence_transformers import SentenceTransformer; model = SentenceTransformer('all-MiniLM-L6-v2')" # RUN python -c "from sentence_transformers import SentenceTransformer; model = SentenceTransformer('all-MiniLM-L6-v2')"
COPY ./backend . COPY ./backend .

View file

@ -19,6 +19,7 @@ from langchain_community.document_loaders import (
PyPDFLoader, PyPDFLoader,
CSVLoader, CSVLoader,
Docx2txtLoader, Docx2txtLoader,
UnstructuredEPubLoader,
UnstructuredWordDocumentLoader, UnstructuredWordDocumentLoader,
UnstructuredMarkdownLoader, UnstructuredMarkdownLoader,
UnstructuredXMLLoader, UnstructuredXMLLoader,
@ -187,6 +188,8 @@ def store_doc(
loader = TextLoader(file_path) loader = TextLoader(file_path)
elif file_ext in octet_markdown: elif file_ext in octet_markdown:
loader = UnstructuredMarkdownLoader(file_path) loader = UnstructuredMarkdownLoader(file_path)
elif file.content_type == "application/epub+zip":
loader = UnstructuredEPubLoader(file_path)
else: else:
loader = TextLoader(file_path) loader = TextLoader(file_path)
known_type=False known_type=False
@ -209,6 +212,12 @@ def store_doc(
) )
except Exception as e: except Exception as e:
print(e) print(e)
if "No pandoc was found" in str(e):
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.PANDOC_NOT_INSTALLED,
)
else:
raise HTTPException( raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST, status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.DEFAULT(e), detail=ERROR_MESSAGES.DEFAULT(e),

View file

@ -42,3 +42,5 @@ class ERROR_MESSAGES(str, Enum):
USER_NOT_FOUND = "We could not find what you're looking for :/" USER_NOT_FOUND = "We could not find what you're looking for :/"
API_KEY_NOT_FOUND = "Oops! It looks like there's a hiccup. The API key is missing. Please make sure to provide a valid API key to access this feature." API_KEY_NOT_FOUND = "Oops! It looks like there's a hiccup. The API key is missing. Please make sure to provide a valid API key to access this feature."
MALICIOUS = "Unusual activities detected, please try again in a few minutes." MALICIOUS = "Unusual activities detected, please try again in a few minutes."
PANDOC_NOT_INSTALLED = "Pandoc is not installed on the server. Please contact your administrator for assistance."

View file

@ -24,6 +24,7 @@ pypdf
docx2txt docx2txt
unstructured unstructured
markdown markdown
pypandoc
PyJWT PyJWT
pyjwt[crypto] pyjwt[crypto]

View file

@ -121,6 +121,7 @@
error: '' error: ''
}; };
try {
files = [...files, doc]; files = [...files, doc];
const res = await uploadDocToVectorDB(localStorage.token, '', file); const res = await uploadDocToVectorDB(localStorage.token, '', file);
@ -129,6 +130,11 @@
doc.collection_name = res.collection_name; doc.collection_name = res.collection_name;
files = files; files = files;
} }
} catch (e) {
// Remove the failed doc from the files array
files = files.filter((f) => f.name !== file.name);
toast.error(e);
}
}; };
onMount(() => { onMount(() => {

View file

@ -12,6 +12,7 @@ export const WEB_UI_VERSION = 'v1.0.0-alpha-static';
export const REQUIRED_OLLAMA_VERSION = '0.1.16'; export const REQUIRED_OLLAMA_VERSION = '0.1.16';
export const SUPPORTED_FILE_TYPE = [ export const SUPPORTED_FILE_TYPE = [
'application/epub+zip',
'application/pdf', 'application/pdf',
'text/plain', 'text/plain',
'text/csv', 'text/csv',