DeepSeek modellerine istek gönderme

Python ile DeepSeek Kullanımı

James Chapman

Curriculum Manager, DataCamp

Özet

Together.ai API’sine, modeli ve veri ile model parametrelerini içeren bir istek gönderen bir bilgisayar.

İstek oluşturma

from openai import OpenAI

# DeepSeek API'ye göndermek için: base_url="https://api.deepseek.com"
client = OpenAI(api_key="<TogetherAI API Key>", base_url="https://api.together.xyz/v1")

openai kütüphanesiyle istek oluşturun
OpenAI: Yapay zeka model ve uygulama geliştiricileri (ör. ChatGPT)
base_url: isteği OpenAI’dan DeepSeek sağlayıcısına yönlendirir
api_key: API kimlik doğrulaması (sağlayıcı dokümantasyonuna bakın)

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

İstek oluşturma

from openai import OpenAI
# DeepSeek API'ye göndermek için: 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(

    # DeepSeek'in API'sinde: model="deepseek-chat"
    model="deepseek-ai/DeepSeek-V3",

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

)


print(response)

Yanıt

ChatCompletion(id='ns1zcjp-zqrih-937de597af0fd643', 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=12469585682595789000)], created=1745920244,
model='deepseek-ai/DeepSeek-V3', object='chat.completion', service_tier=None, system_fingerprint=None,
usage=CompletionUsage(completion_tokens=38, prompt_tokens=14, total_tokens=52,
completion_tokens_details=None, prompt_tokens_details=None), prompt=[])

Yanıt

ChatCompletion(id='ns1zcjp-zqrih-937de597af0fd643',
               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=12469585682595789000)],
               created=1745920244,
               model='deepseek-ai/DeepSeek-V3',
               object='chat.completion',
               service_tier=None,
               system_fingerprint=None,
               usage=CompletionUsage(completion_tokens=38, prompt_tokens=14, total_tokens=52,
                                     completion_tokens_details=None, prompt_tokens_details=None),
                                     prompt=[])

Yanıtı yorumlama

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=12469585682595789000)]

Yanıtı yorumlama

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=12469585682595789000)

Yanıtı yorumlama

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.

API kullanım maliyetleri

DeepSeek için:
- Sağlayıcı (ör. together.ai)
- Model
- Daha büyük giriş + çıkış = Daha yüksek maliyet

Bir ücretli yol.

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

Haydi pratik yapalım!

Python ile DeepSeek Kullanımı