Llamaparse

vversa

Guys, yesterday i had llama parse returning an array of documents after parsing (as it should). Today is returning plain text and its breaking some stuff... any news on that?

Plain Text

 parser = LlamaParse(
                result_type="markdown",
                language="pt",
                premium_mode=True if mode == "premium" else False,
                split_by_page=False,
                disable_ocr=True,
                skip_diagonal_text=True,
                **parse_params,
            )

            start_parse = timer()

            file_extractor = {".pdf": parser}
            documents = SimpleDirectoryReader(
                input_files=[file_path], file_extractor=file_extractor
            ).load_data()

4 comments

WWhiteFang_Jr

@Sacha Bron could you please take a look into this🙏

vversa

actually it is working for other PDFs, just ignore it for now, i'll try to get more info

WWhiteFang_Jr

I see, maybe there is some issue in your file?

vversa

Got it!

Plain Text

print("Parsing nodes...")
            node_parser = MarkdownElementNodeParser(
                llm=llama_utils.create_openai_llm(model="gpt-4o-mini"), num_workers=8
            )
            nodes = node_parser.get_nodes_from_documents(documents)
            print("Nodes parsed")

for some reason gpt-4o-mini response is causing this error... it is working with gpt-4o

Sorry about that

Attachment

Add a reply

Find answers from the community

Llamaparse