The Quick Start Ready Made Template Example doesnt work

[msanaulla]

The Ready made template example given in: https://haystack.deepset.ai/overview/quick-start doesnt work.

This is the code I tried:

import os
from dotenv import load_dotenv
from haystack import Pipeline, PredefinedPipeline
load_dotenv()

pipeline = Pipeline.from_template(PredefinedPipeline.CHAT_WITH_WEBSITE)
result = pipeline.run({
    "fetcher": {"urls": ["https://haystack.deepset.ai/overview/quick-start"]},
    "prompt": {"query": "Which components do I need for a RAG pipeline?"}}
)
print(result["llm"]["replies"][0])

I get the below error:

metadata: {}
PS D:\projects\python-demo> & C:/Users/msanaulla/AppData/Local/Programs/Python/Python312/python.exe d:/projects/python-demo/haystack
PS D:\projects\python-demo> & C:/Users/msanaulla/AppData/Local/Programs/Python/Python312/python.exe d:/projects/python-demo/haystack-demo.py
Traceback (most recent call last):
  File "C:\Users\msanaulla\AppData\Local\Programs\Python\Python312\Lib\site-packages\haystack\core\pipeline\base.py", line 186, in f
  File "C:\Users\msanaulla\AppData\Local\Programs\Python\Python312\Lib\site-packages\haystack\core\pipeline\base.py", line 186, in from_dict
    instance = component_from_dict(component_class, component_data, name, callbacks)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\msanaulla\AppData\Local\Programs\Python\Python312\Lib\site-packages\haystack\core\serialization.py", line 118, in c
  File "C:\Users\msanaulla\AppData\Local\Programs\Python\Python312\Lib\site-packages\haystack\core\serialization.py", line 118, in component_from_dict
    return do_from_dict()
           ^^^^^^^^^^^^^^
  File "C:\Users\msanaulla\AppData\Local\Programs\Python\Python312\Lib\site-packages\haystack\core\serialization.py", line 113, in d
  File "C:\Users\msanaulla\AppData\Local\Programs\Python\Python312\Lib\site-packages\haystack\core\serialization.py", line 113, in do_from_dict
    return cls.from_dict(data)
           ^^^^^^^^^^^^^^^^^^^
  File "C:\Users\msanaulla\AppData\Local\Programs\Python\Python312\Lib\site-packages\haystack\components\converters\html.py", line 6
  File "C:\Users\msanaulla\AppData\Local\Programs\Python\Python312\Lib\site-packages\haystack\components\converters\html.py", line 67, in from_dict
    return default_from_dict(cls, data)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\msanaulla\AppData\Local\Programs\Python\Python312\Lib\site-packages\haystack\core\serialization.py", line 192, in d
  File "C:\Users\msanaulla\AppData\Local\Programs\Python\Python312\Lib\site-packages\haystack\core\serialization.py", line 192, in default_from_dict
    return cls(**init_params)
           ^^^^^^^^^^^^^^^^^^
  File "C:\Users\msanaulla\AppData\Local\Programs\Python\Python312\Lib\site-packages\haystack\core\component\component.py", line 254
  File "C:\Users\msanaulla\AppData\Local\Programs\Python\Python312\Lib\site-packages\haystack\core\component\component.py", line 254, in __call__
    instance = super().__call__(*args, **kwargs)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: HTMLToDocument.__init__() got an unexpected keyword argument 'extractor_type'

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "C:\Users\msanaulla\AppData\Local\Programs\Python\Python312\Lib\site-packages\haystack\core\pipeline\base.py", line 849, in f
  File "C:\Users\msanaulla\AppData\Local\Programs\Python\Python312\Lib\site-packages\haystack\core\pipeline\base.py", line 849, in from_template
    return cls.loads(rendered)
           ^^^^^^^^^^^^^^^^^^^
  File "C:\Users\msanaulla\AppData\Local\Programs\Python\Python312\Lib\site-packages\haystack\core\pipeline\base.py", line 258, in l
  File "C:\Users\msanaulla\AppData\Local\Programs\Python\Python312\Lib\site-packages\haystack\core\pipeline\base.py", line 258, in loads
    return cls.from_dict(deserialized_data, callbacks)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\msanaulla\AppData\Local\Programs\Python\Python312\Lib\site-packages\haystack\core\pipeline\base.py", line 195, in f
  File "C:\Users\msanaulla\AppData\Local\Programs\Python\Python312\Lib\site-packages\haystack\core\pipeline\base.py", line 195, in from_dict
    raise DeserializationError(msg) from e
haystack.core.errors.DeserializationError: Couldn't deserialize component 'converter' of class 'HTMLToDocument' with the following d
haystack.core.errors.DeserializationError: Couldn't deserialize component 'converter' of class 'HTMLToDocument' with the following data: {'init_parameters': {'extractor_type': 'DefaultExtractor'}, 'type': 'haystack.components.converters.html.HTMLToDocument'}. Poss
haystack.core.errors.DeserializationError: 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 chan
haystack.core.errors.DeserializationError: 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.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "d:\projects\python-demo\haystack-demo.py", line 7, in <module>
    pipeline = Pipeline.from_template(PredefinedPipeline.CHAT_WITH_WEBSITE)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\msanaulla\AppData\Local\Programs\Python\Python312\Lib\site-packages\haystack\core\pipeline\base.py", line 853, in f
  File "C:\Users\msanaulla\AppData\Local\Programs\Python\Python312\Lib\site-packages\haystack\core\pipeline\base.py", line 853, in from_template
    raise PipelineUnmarshalError(msg)
haystack.core.errors.PipelineUnmarshalError: Error unmarshalling pipeline: Couldn't deserialize component 'converter' of class 'HTML
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.conver
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 lo
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.
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: {}

I am using below Haystack version:

PS D:\projects\python-demo> pip show haystack-ai                                                                                    
Name: haystack-ai
Version: 2.5.1
Summary: LLM framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data.
Home-page: https://github.com/deepset-ai/haystack
Author:
Author-email: "deepset.ai" <[email protected]>
License:
Location: C:\Users\msanaulla\AppData\Local\Programs\Python\Python312\Lib\site-packages
Requires: haystack-experimental, jinja2, lazy-imports, more-itertools, networkx, numpy, openai, pandas, posthog, python-dateutil, pyyaml, requests, tenacity, tqdm, typing-extensions
Required-by: haystack-experimental

[bilgeyucel]

Thanks for opening the issue @msanaulla, I can reproduce the error in this colab with Haystack 2.6.0 as well

[anakin87]

The original error was fixed in #8401.

If you install trafilatura (specified in the Quick start), the error in the notebook disappears.

@bilgeyucel feel free to close the issue if it works.

[bilgeyucel]

Yes, that fixes the issue! Thank you @anakin87!