feat: support ollama.com structured-outputs Support ollama structured output.

[willshang76]

Description

Now ollama supports structured output.

Motivation and Context

close #1290

• I have raised an issue to propose this change (required for new features and bug fixes)

Types of changes

What types of changes does your code introduce? Put an x in all the boxes that apply:

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds core functionality)
• Breaking change (fix or feature that would cause existing functionality to change)
• Documentation (update in the documentation)
• Example (update in the folder of example)

Implemented Tasks

• Subtask 1
• Subtask 2
• Subtask 3

Checklist

Go over all the following points, and put an x in all the boxes that apply.
If you are unsure about any of these, don't hesitate to ask. We are here to help!

• I have read the CONTRIBUTION guide. (required)
• My change requires a change to the documentation.
• I have updated the tests accordingly. (required for a bug fix or a new feature)
• I have updated the documentation accordingly.

[MuggleJinx]

Overall looks good!

[MuggleJinx]

However, I failed to run the example... The model failed to produce a valid json format and the pydantic validation failed. Other reviewers can double check with this..

[Wendong-Fan]

Thanks @willshang76 , seems currently the example code can't run as expected

Ollama server started on http://localhost:11434/v1 for llama3.2 model.
2024-12-11 21:53:27,666 - httpx - INFO - HTTP Request: POST http://localhost:11434/v1/chat/completions "HTTP/1.1 200 OK"
2024-12-11 21:53:27,674 - camel.models.model_manager - ERROR - Error processing with model: <camel.models.ollama_model.OllamaModel object at 0x10628fb60>
2024-12-11 21:53:27,674 - camel.agents.chat_agent - ERROR - An error occurred while running model llama3.2, index: 0
Traceback (most recent call last):
  File "/Users/enrei/Desktop/camel_1127/camel/camel/agents/chat_agent.py", line 965, in _step_model_response
    response = self.model_backend.run(openai_messages)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/enrei/Desktop/camel_1127/camel/camel/models/model_manager.py", line 211, in run
    raise exc
  File "/Users/enrei/Desktop/camel_1127/camel/camel/models/model_manager.py", line 201, in run
    response = self.current_model.run(messages)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/enrei/Desktop/camel_1127/camel/camel/models/ollama_model.py", line 142, in run
    response = self._client.beta.chat.completions.parse(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/enrei/Library/Caches/pypoetry/virtualenvs/camel-ai-gf_ewcJG-py3.12/lib/python3.12/site-packages/openai/resources/beta/chat/completions.py", line 156, in parse
    return self._post(
           ^^^^^^^^^^^
  File "/Users/enrei/Library/Caches/pypoetry/virtualenvs/camel-ai-gf_ewcJG-py3.12/lib/python3.12/site-packages/openai/_base_client.py", line 1280, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/enrei/Library/Caches/pypoetry/virtualenvs/camel-ai-gf_ewcJG-py3.12/lib/python3.12/site-packages/openai/_base_client.py", line 957, in request
    return self._request(
           ^^^^^^^^^^^^^^
  File "/Users/enrei/Library/Caches/pypoetry/virtualenvs/camel-ai-gf_ewcJG-py3.12/lib/python3.12/site-packages/openai/_base_client.py", line 1063, in _request
    return self._process_response(
           ^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/enrei/Library/Caches/pypoetry/virtualenvs/camel-ai-gf_ewcJG-py3.12/lib/python3.12/site-packages/openai/_base_client.py", line 1162, in _process_response
    return api_response.parse()
           ^^^^^^^^^^^^^^^^^^^^
  File "/Users/enrei/Library/Caches/pypoetry/virtualenvs/camel-ai-gf_ewcJG-py3.12/lib/python3.12/site-packages/openai/_response.py", line 319, in parse
    parsed = self._options.post_parser(parsed)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/enrei/Library/Caches/pypoetry/virtualenvs/camel-ai-gf_ewcJG-py3.12/lib/python3.12/site-packages/openai/resources/beta/chat/completions.py", line 150, in parser
    return _parse_chat_completion(
           ^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/enrei/Library/Caches/pypoetry/virtualenvs/camel-ai-gf_ewcJG-py3.12/lib/python3.12/site-packages/openai/lib/_parsing/_completions.py", line 110, in parse_chat_completion
    "parsed": maybe_parse_content(
              ^^^^^^^^^^^^^^^^^^^^
  File "/Users/enrei/Library/Caches/pypoetry/virtualenvs/camel-ai-gf_ewcJG-py3.12/lib/python3.12/site-packages/openai/lib/_parsing/_completions.py", line 161, in maybe_parse_content
    return _parse_content(response_format, message.content)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/enrei/Library/Caches/pypoetry/virtualenvs/camel-ai-gf_ewcJG-py3.12/lib/python3.12/site-packages/openai/lib/_parsing/_completions.py", line 221, in _parse_content
    return cast(ResponseFormatT, model_parse_json(response_format, content))
                                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/enrei/Library/Caches/pypoetry/virtualenvs/camel-ai-gf_ewcJG-py3.12/lib/python3.12/site-packages/openai/_compat.py", line 169, in model_parse_json
    return model.model_validate_json(data)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/enrei/Library/Caches/pypoetry/virtualenvs/camel-ai-gf_ewcJG-py3.12/lib/python3.12/site-packages/pydantic/main.py", line 625, in model_validate_json
    return cls.__pydantic_validator__.validate_json(json_data, strict=strict, context=context)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
pydantic_core._pydantic_core.ValidationError: 1 validation error for PetList
  Invalid JSON: expected ident at line 1 column 2 [type=json_invalid, input_value="It sounds like you have ...ties in your household?", input_type=str]
    For further information visit https://errors.pydantic.dev/2.9/v/json_invalid
Traceback (most recent call last):
  File "/Users/enrei/Desktop/camel_1127/camel/examples/models/ollama_model_example.py", line 83, in <module>
    assistant_response = agent.step(user_msg)
                         ^^^^^^^^^^^^^^^^^^^^
  File "/Users/enrei/Desktop/camel_1127/camel/camel/agents/chat_agent.py", line 540, in step
    ) = self._step_model_response(openai_messages, num_tokens)
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/enrei/Desktop/camel_1127/camel/camel/agents/chat_agent.py", line 976, in _step_model_response
    raise ModelProcessingError(
camel.models.model_manager.ModelProcessingError: Unable to process messages: none of the provided models run succesfully.
(camel-ai-py3.12) 

[willshang76]

Based on the allama doc(https://ollama.com/blog/structured-outputs), you need to install the latest version of allama to make it work.

[Wendong-Fan]

Thanks @willshang76 !