import openai
openai.api_key = "your_sk"
# 提示（假設(shè)md_resume和job_description已經(jīng)被定義）
prompt = f"""
我有一份用Markdown格式編寫的簡歷和一份工作描述。
請(qǐng)根據(jù)工作要求調(diào)整我的簡歷，同時(shí)保持專業(yè)語氣。調(diào)整我的技能、經(jīng)驗(yàn)和成就，以突出與職位最相關(guān)的點(diǎn)。
確保我的簡歷仍然反映我獨(dú)特的資格和優(yōu)勢，但強(qiáng)調(diào)與工作描述匹配的技能和經(jīng)驗(yàn)。
確保我的經(jīng)驗(yàn)以符合所需資格的方式呈現(xiàn)。
保持清晰、簡潔和專業(yè)。
以Markdown格式返回更新后的簡歷。
"""
# 調(diào)用API
response = openai.chat.completions.create(
model="gpt-4o-mini",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": prompt}
],
temperature = 0.25
)
# 提取響應(yīng)
resume = response.choices[0].message.content

import re
from youtube_transcript_api import YouTubeTranscriptApi
youtube_url = "video link here"
# 使用正則表達(dá)式提取視頻ID
video_id_regex = r'(?:v=|\/)([0-9A-Za-z_-]{11}).*'
match = re.search(video_id_regex, youtube_url)
if match:
return match.group(1)
else:
return None
# 提取文稿
text_list = [transcript[i]['text'] for i in range(len(transcript))]
transcript_text = '\n'.join(text_list)

from sentence_transformers import SentenceTransformer
# 加載嵌入模型
model = SentenceTransformer("all-MiniLM-L6-v2")
# 將摘要存儲(chǔ)在列表中
abstract_list = ["摘要1", "摘要2"]
# 計(jì)算嵌入
embeddings = model.encode(abstract_list)

import fitz  # PyMuPDF

def extract_text_chunks(pdf_path, chunk_size, overlap_size):
    # 打開PDF文件
    pdf_document = fitz.open(pdf_path)
    chunks = []

    # 遍歷PDF的每一頁
    for page_num in range(len(pdf_document)):
        page = pdf_document[page_num]
        page_text = page.get_text()

        # 將當(dāng)前頁面的文本分割成有重疊的塊
        start = 0
        while start < len(page_text):
            end = start + chunk_size
            chunk = page_text[start:end]

            # 將頁碼與文本塊一起保存
            chunks.append((page_num + 1, chunk))
            # 移動(dòng)到下一個(gè)有重疊的塊
            start += chunk_size - overlap_size
    
    return chunks

# 提取參數(shù)
pdf_path = "your_file.pdf"
chunk_size = 1000  # 每個(gè)文本塊的字符數(shù)
overlap_size = 200  # 重疊的字符數(shù)

text_chunks = extract_text_chunks_with_page_numbers(pdf_path, chunk_size, overlap_size)

# 顯示帶有頁碼的文本塊
for i, (page_number, chunk) in enumerate(text_chunks):
    print(f"Chunk {i + 1} (Page {page_number}):\n{chunk}\n{'-' * 50}")

import gradio as gr

def generate_response(message, history):
    # 生成響應(yīng)的代碼
    return response

demo = gr.ChatInterface(
    fn=generate_response,
    examples=[{"text": "Hello", "files": []}], 
    title="Echo Bot", 
    multimodal=True
)
demo.launch()