with_structured_output

from pydantic import BaseModel
from langchain_google_vertexai import ChatVertexAI

class AnswerWithJustification(BaseModel):
    '''An answer to the user question along with justification for the answer.'''

    answer: str
    justification: str

llm = ChatVertexAI(model_name="gemini-2.0-flash-001", temperature=0)
structured_llm = llm.with_structured_output(AnswerWithJustification)

structured_llm.invoke(
    "What weighs more a pound of bricks or a pound of feathers"
)
# -> AnswerWithJustification(
#     answer='They weigh the same.', justification='A pound is a pound.'
# )

from pydantic import BaseModel
from langchain_google_vertexai import ChatVertexAI

class AnswerWithJustification(BaseModel):
    '''An answer to the user question along with justification for the answer.'''

    answer: str
    justification: str

llm = ChatVertexAI(model_name="gemini-2.0-flash-001", temperature=0)
structured_llm = llm.with_structured_output(
    AnswerWithJustification, include_raw=True
)

structured_llm.invoke(
    "What weighs more a pound of bricks or a pound of feathers"
)
# -> {
#     'raw': AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_Ao02pnFYXD6GN1yzc0uXPsvF', 'function': {'arguments': '{"answer":"They weigh the same.","justification":"Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume or density of the objects may differ."}', 'name': 'AnswerWithJustification'}, 'type': 'function'}]}),
#     'parsed': AnswerWithJustification(answer='They weigh the same.', justification='Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume or density of the objects may differ.'),
#     'parsing_error': None
# }

from pydantic import BaseModel
from langchain_core.utils.function_calling import (
    convert_to_openai_function,
)
from langchain_google_vertexai import ChatVertexAI

class AnswerWithJustification(BaseModel):
    '''An answer to the user question along with justification for the answer.'''

    answer: str
    justification: str

dict_schema = convert_to_openai_function(AnswerWithJustification)
llm = ChatVertexAI(model_name="gemini-2.0-flash-001", temperature=0)
structured_llm = llm.with_structured_output(dict_schema)

structured_llm.invoke(
    "What weighs more a pound of bricks or a pound of feathers"
)
# -> {
#     'answer': 'They weigh the same',
#     'justification': 'Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume and density of the two substances differ.'
# }

from pydantic import BaseModel, Field
from langchain_google_vertexai import ChatVertexAI

class Explanation(BaseModel):
    '''A topic explanation with examples.'''

    description: str = Field(
        description="A brief description of the topic."
    )
    examples: str = Field(description="Two examples related to the topic.")

llm = ChatVertexAI(model_name="gemini-2.0-flash", temperature=0)
structured_llm = llm.with_structured_output(Explanation, method="json_mode")

for chunk in structured_llm.stream("Tell me about transformer models"):
    print(chunk)
    print("-------------------------")
# -> description='Transformer models are a type of neural network architecture that have revolutionized the field of natural language processing (NLP) and are also increasingly used in computer vision and other domains. They rely on the self-attention mechanism to weigh the importance of different parts of the input data, allowing them to effectively capture long-range dependencies. Unlike recurrent neural networks (RNNs), transformers can process the entire input sequence in parallel, leading to significantly faster training times. Key components of transformer models include: the self-attention mechanism (calculates attention weights between different parts of the input), multi-head attention (performs self-attention multiple times with different learned parameters), positional encoding (adds information about the position of tokens in the input sequence), feedforward networks (applies a non-linear transformation to each position), and encoder-decoder structure (used for sequence-to-sequence tasks).' examples='1. BERT (Bidirectional Encoder Representations from Transformers): A pre-trained transformer'
#    -------------------------
#    description='Transformer models are a type of neural network architecture that have revolutionized the field of natural language processing (NLP) and are also increasingly used in computer vision and other domains. They rely on the self-attention mechanism to weigh the importance of different parts of the input data, allowing them to effectively capture long-range dependencies. Unlike recurrent neural networks (RNNs), transformers can process the entire input sequence in parallel, leading to significantly faster training times. Key components of transformer models include: the self-attention mechanism (calculates attention weights between different parts of the input), multi-head attention (performs self-attention multiple times with different learned parameters), positional encoding (adds information about the position of tokens in the input sequence), feedforward networks (applies a non-linear transformation to each position), and encoder-decoder structure (used for sequence-to-sequence tasks).' examples='1. BERT (Bidirectional Encoder Representations from Transformers): A pre-trained transformer model that can be fine-tuned for various NLP tasks like text classification, question answering, and named entity recognition. 2. GPT (Generative Pre-trained Transformer): A language model that uses transformers to generate coherent and contextually relevant text. GPT models are used in chatbots, content creation, and code generation.'
#    -------------------------