python - 如何使用 Codex API 获取 token 或代码嵌入？

Question

对于给定的代码片段，如何使用 Codex API 进行嵌入？

import os
import openai
import config


openai.api_key = config.OPENAI_API_KEY

def runSomeCode():
    response = openai.Completion.create(
      engine="code-davinci-001",
      prompt="\"\"\"\n1. Get a reputable free news api\n2. Make a request to the api for the latest news stories\n\"\"\"",
      temperature=0,
      max_tokens=1500,
      top_p=1,
      frequency_penalty=0,
      presence_penalty=0)

    if 'choices' in response:
        x = response['choices']
        if len(x) > 0:
            return x[0]['text']
        else:
            return ''
    else:
        return ''



answer = runSomeCode()
print(answer)

但是我想弄清楚给定一个如下所示的 python 代码块，我可以从 codex 获取嵌入吗？

输入:

import Random
a = random.randint(1,12)
b = random.randint(1,12)
for i in range(10):
    question = "What is "+a+" x "+b+"? "
    answer = input(question)
    if answer = a*b
        print (Well done!)
    else:
        print("No.")

输出:

• 嵌入输入代码

Answer 1

是的，OpenAI 可以为任何输入文本创建嵌入——即使它是代码。您只需要在其 get_embedding() 函数调用中传递正确的引擎或模型。我测试了这段代码:

# Third-party imports
import openai

from openai.embeddings_utils import get_embedding


openai.api_key = OPENAI_SEC_KEY


embedding = get_embedding("""
    def sample_code():
        print("Hello from IamAshKS !!!")
""", engine="code-search-babbage-code-001")

print()
print(f"{embedding=}")
print(f"{len(embedding)=}")

# OUTPUT:
# embedding=[-0.007094269152730703, 0.006055716425180435, -0.005044757854193449, ...]
# len(embedding)=2048


embedding = get_embedding("""
import Random
a = random.randint(1,12)
b = random.randint(1,12)
for i in range(10):
    question = "What is "+a+" x "+b+"? "
    answer = input(question)
    if answer = a*b
        print (Well done!)
    else:
        print("No.")
""", engine="code-search-babbage-code-001")

print()
print(f"{embedding=}")
print(f"{len(embedding)=}")

# OUTPUT:
# embedding=[-0.011341490782797337, -0.005919027142226696, 0.0011923711281269789, ...]
# len(embedding)=2048

注意:您可以使用 get_embedding() 的 engine 参数替换模型或引擎。

上面给出的代码为您提供了任何代码的嵌入。还有另一个名为 code-search-ada-code-001 的代码搜索引擎/模型，但它不如 code-search-babbage-code-001 强大，我用于此答案。如果您还想进行代码搜索，请阅读下面的引用资料。

引用资料:

• https://openai.com/blog/introducing-text-and-code-embeddings/
• https://beta.openai.com/docs/guides/embeddings/code-search-embeddings
• https://beta.openai.com/docs/guides/embeddings/use-cases#expander-7