Fazendo requisições a modelos DeepSeek

Trabalhando com DeepSeek em Python

James Chapman

AI Curriculum Lead, DataCamp

Recapitulando

Um computador enviando uma requisição para a API da Together.ai, que contém o modelo e quaisquer dados e parâmetros do modelo.

Criando uma requisição

from openai import OpenAI

# To send to DeepSeek API: base_url="https://api.deepseek.com"
client = OpenAI(api_key="<TogetherAI API Key>", base_url="https://api.together.xyz/v1")

Crie requisições usando a biblioteca openai
OpenAI: desenvolvedores de modelos e apps de IA (por exemplo, ChatGPT)
base_url: redirecione a requisição de OpenAI para o provedor de modelos DeepSeek
api_key: autenticação da API (veja a documentação do provedor)

¹ https://platform.deepseek.com/api_keys

Criando uma requisição

from openai import OpenAI
# To send to DeepSeek API: base_url="https://api.deepseek.com"
client = OpenAI(api_key="<TogetherAI API Key>", base_url="https://api.together.xyz/v1")


response = client.chat.completions.create(

    model="deepseek-ai/DeepSeek-V4-Pro",

    messages=[{"role": "user",
               "content": "In one sentence, what is hallucination in AI?"}]

)


print(response)

A resposta

ChatCompletion(id='onVWeEx-gBAtS-a09121fcae54578c', choices=[Choice(finish_reason='stop', index=0,
logprobs=None, message=ChatCompletionMessage(content='Hallucination in AI is when a model confidently
generates information that sounds plausible but is factually incorrect, misleading, or entirely
fabricated.', refusal=None, role='assistant', annotations=None, audio=None, function_call=None,
tool_calls=[]), seed=None)], created=1781018557, model='deepseek-ai/DeepSeek-V4-Pro',
object='chat.completion', moderation=None, service_tier=None, system_fingerprint='default',
usage=CompletionUsage(completion_tokens=28, prompt_tokens=15, total_tokens=43,
completion_tokens_details=None, prompt_tokens_details=PromptTokensDetails(audio_tokens=None,
cached_tokens=0)), prompt=[])

A resposta

ChatCompletion(id='onVWeEx-gBAtS-a09121fcae54578c',
               choices=[Choice(finish_reason='stop', index=0, logprobs=None,
                               message=ChatCompletionMessage(content='Hallucination in AI refers...',
                               refusal=None, role='assistant', annotations=None, audio=None,
                               function_call=None, tool_calls=[]), seed=None)],
               created=1781018557,
               model='deepseek-ai/DeepSeek-V4-Pro',
               object='chat.completion',
               moderation=None,
               service_tier=None,
               system_fingerprint='default',
               usage=CompletionUsage(completion_tokens=28, prompt_tokens=15, total_tokens=43,
                                     completion_tokens_details=None,
                                     prompt_tokens_details=PromptTokensDetails(audio_tokens=None,
                                          cached_tokens=0)),
               prompt=[])

Interpretando a resposta

print(response.choices)

[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(
content='Hallucination in AI refers to the generation of false or nonsensical information
that is presented as factual, often due to limitations in training data, model biases, or
inference errors.', refusal=None, role='assistant', annotations=None, audio=None,
function_call=None, tool_calls=[]), seed=None)]

Interpretando a resposta

print(response.choices[0])

Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(
content='Hallucination in AI refers to the generation of false or nonsensical information
that is presented as factual, often due to limitations in training data, model biases, or
inference errors.', refusal=None, role='assistant', annotations=None, audio=None,
function_call=None, tool_calls=[]), seed=None)

Interpretando a resposta

print(response.choices[0].message)

ChatCompletionMessage(content='Hallucination in AI refers to the generation of false or
nonsensical information that is presented as factual, often due to limitations in training
data, model biases, or inference errors.', refusal=None, role='assistant', annotations=None,
audio=None, function_call=None, tool_calls=[])

print(response.choices[0].message.content)

Hallucination in AI refers to the generation of false or nonsensical information that is
presented as factual, often due to limitations in training data, model biases, or inference
errors.

Custos de uso da API

Para DeepSeek:
- Provedor (ex.: together.ai)
- Modelo
- Entradas + saídas maiores = custo maior

Uma estrada com pedágio.

¹ https://api-docs.deepseek.com/quick_start/pricing

Vamos praticar!

Trabalhando com DeepSeek em Python