PredefinedPipeline.CHAT_WITH_WEBSITE fails deserialization

[silvanocerza]

Discussed in #8390

^{Originally posted by aillusions September 24, 2024}
Hi

I'e tried 2 sample apps from this guide https://haystack.deepset.ai/overview/quick-start and none of them have worked ..

Env:

python --version
  Python 3.12.6

pip show haystack-ai
   Name: haystack-ai
   Version: 2.5.1

first of them throws error:

haystack.core.errors.PipelineUnmarshalError: Error unmarshalling pipeline: Couldn't deserialize component 'converter' of class 'HTMLToDocument' with the following data: {'init_parameters': {'extractor_type': 'DefaultExtractor'}, 'type': 'haystack.components.converters.html.HTMLToDocument'}. Possible reasons include malformed serialized data, mismatch between the serialized component and the loaded one (due to a breaking change, see https://github.com/deepset-ai/haystack/releases), etc.

second

ssl.SSLCertVerificationError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: self-signed certificate in certificate chain (_ssl.c:1000)

How to troubleshoot those?

thx

---

To reproduce:

from haystack import Pipeline, PredefinedPipeline

Pipeline.from_template(PredefinedPipeline.CHAT_WITH_WEBSITE)

It will fail with this error:

PipelineUnmarshalError: Error unmarshalling pipeline: Couldn't deserialize component 'converter' of class 'HTMLToDocument' with the following data: {'init_parameters': {'extractor_type': 'DefaultExtractor'}, 'type': 'haystack.components.converters.html.HTMLToDocument'}. Possible reasons include malformed serialized data, mismatch between the serialized component and the loaded one (due to a breaking change, see https://github.com/deepset-ai/haystack/releases), etc.
Source:
components:
  converter:
    init_parameters:
      extractor_type: DefaultExtractor
    type: haystack.components.converters.html.HTMLToDocument

  fetcher:
    init_parameters:
      raise_on_failure: true
      retry_attempts: 2
      timeout: 3
      user_agents:
      - haystack/LinkContentFetcher/2.0.0b8
    type: haystack.components.fetchers.link_content.LinkContentFetcher

  llm:
    init_parameters:
      api_base_url: null
      api_key:
        env_vars:
        - OPENAI_API_KEY
        strict: true
        type: env_var
      generation_kwargs: {}
      model: gpt-3.5-turbo
      streaming_callback: null
      system_prompt: null
    type: haystack.components.generators.openai.OpenAIGenerator

  prompt:
    init_parameters:
      template: |

        "According to the contents of this website:
        {% for document in documents %}
          {{document.content}}
        {% endfor %}
        Answer the given question: {{query}}
        Answer:
        "
    type: haystack.components.builders.prompt_builder.PromptBuilder

connections:
- receiver: converter.sources
  sender: fetcher.streams
- receiver: prompt.documents
  sender: converter.documents
- receiver: llm.prompt
  sender: prompt.prompt

metadata: {}

This probably stems from the change in the HTMLToDocument backend change from boilerpy3 to trafilatura coming from #7705.