Haystack component with the name 'PDFToTextConverter' not found.

[pnpds1]

Hello guys,
I have cloned the haystack repository from the haystack github repo and then done pip install . After that I have downloaded and installed xpdf too. Even after that when I run the rest api I am encountering this error. I am using this command to run the api.
gunicorn rest_api.application:app -b 0.0.0.0:8000 -k uvicorn.workers.UvicornWorker -t 300

I am attahching the screenshot of the error that I am getting right now.

Kindly help me to solve this issue. This is very urgent. Thank you so much in advance.

[mayankjobanputra]

@pnpds1 can you please confirm a few things here?

1. How exactly you installed Haystack? (i.e., full command) and what version of Haystack are you running?
2. I am assuming you're on Ubuntu platform. Correct me if I am wrong.
3. How did you install xpdf and what version of xpdf are you running?

[pnpds1]

1. I did git clone https://github.com/deepset-ai/haystack.git.
   cd haystack
   pip install .

2. Yes I am on Ubuntu platform.

3. wget --no-check-certificate https://dl.xpdfreader.com/xpdf-tools-linux-4.04.tar.gz &&
   tar -xvf xpdf-tools-linux-4.04.tar.gz && cp xpdf-tools-linux-4.04/bin64/pdftotext /usr/local/bin

[mayankjobanputra]

can you try pip install -e '.[all]' or pip install -e '.[all-gpu]' in case you want to use GPU?

If this doesn't work can you also share your pipeline.yml here?

[pnpds1]

This is my pipeline.yml

_# To allow your IDE to autocomplete and validate your YAML pipelines, name them as .haystack-pipeline.yml

version: ignore

components: # define all the building-blocks for Pipeline

• name: DocumentStore
  type: ElasticsearchDocumentStore
  params:
  host: localhost
• name: Retriever
  type: BM25Retriever
  params:
  document_store: DocumentStore # params can reference other components defined in the YAML
  top_k: 5
• name: Reader # custom-name for the component; helpful for visualization & debugging
  type: FARMReader # Haystack Class name for the component
  params:
  model_name_or_path: deepset/roberta-base-squad2
  context_window_size: 500
  return_no_answer: true
• name: TextFileConverter
  type: TextConverter
• name: PDFFileConverter
  type: PDFToTextConverter
• name: Preprocessor
  type: PreProcessor
  params:
  split_by: word
  split_length: 1000
• name: FileTypeClassifier
  type: FileTypeClassifier

pipelines:

• name: query # a sample extractive-qa Pipeline
  nodes:
  • name: Retriever
    inputs: [Query]
  • name: Reader
    inputs: [Retriever]
• name: indexing
  nodes:
  • name: FileTypeClassifier
    inputs: [File]
  • name: TextFileConverter
    inputs: [FileTypeClassifier.output_1]
  • name: PDFFileConverter
    inputs: [FileTypeClassifier.output_2]
  • name: Preprocessor
    inputs: [PDFFileConverter, TextFileConverter]
  • name: Retriever
    inputs: [Preprocessor]
  • name: DocumentStore
    inputs: [Retriever]_

[mayankjobanputra]

@pnpds1 I am assuming this is same as the sample dpr pipeline provided by Haystack?

Did you try to install using pip install -e '.[all]' or pip install -e '.[all-gpu]' in case you want to use GPU? Any luck?

[pnpds1]

@mayankjobanputra I tried pip install -e '.[ocr]' . It worked. Thanks a lot for your valuable suggestions.