Spaces:
Sleeping
Sleeping
| from langchain.prompts import ChatPromptTemplate | |
| from langchain.output_parsers import ResponseSchema | |
| from langchain.output_parsers import StructuredOutputParser | |
| from langchain_core.output_parsers import StrOutputParser | |
| from scrap_post import scrappost | |
| import requests | |
| def is_shortened_url(url): # It is checking whether it is a shorten url or regular website url | |
| try: | |
| response = requests.head(url, allow_redirects=True) | |
| final_url = response.url | |
| if final_url != url: | |
| return True | |
| return False | |
| except requests.exceptions.RequestException as e: | |
| print("Error:", e) | |
| return False | |
| def expand_short_url(short_url): # It is converting shorten url to regular url | |
| try: | |
| response = requests.head(short_url, allow_redirects=True) | |
| if response.status_code == 200: | |
| return response.url | |
| else: | |
| print("Error: Short URL couldn't be expanded.") | |
| return None | |
| except requests.exceptions.RequestException as e: | |
| print("Error:", e) | |
| return None | |
| def get_original_url(url): | |
| if is_shortened_url(url): | |
| return expand_short_url(url) | |
| else: | |
| return url | |
| # Below function extract the post only content from complete web page content and parraphrase the extracted post | |
| def paraphrased_post(url,model): | |
| post=scrappost(url) | |
| # print(post) | |
| template="""You are a helpful paraphraser tool. You are provided with a content and your task is to paraphrase it. | |
| {data}""" | |
| prompt = ChatPromptTemplate.from_template(template) | |
| chain = prompt | model | StrOutputParser() | |
| phrased_post=chain.invoke({"data":post}) | |
| data2=extract_data(phrased_post , model) | |
| keywords=data2['Keywords'][:3] | |
| take_aways=data2['Take Aways'][:3] | |
| highlights=data2['Highlights'][:3] | |
| return phrased_post,keywords , take_aways, highlights | |
| # Below function extract the details such as keywords , Take aways , highlights and questions | |
| def extract_data(post_data ,model): | |
| keywords = ResponseSchema(name="Keywords", | |
| description="These are the keywords extracted from LinkedIn post",type="list") | |
| Take_aways = ResponseSchema(name="Take Aways", | |
| description="These are the take aways extracted from LinkedIn post", type= "list") | |
| Highlights=ResponseSchema(name="Highlights", | |
| description="These are the highlights extracted from LinkedIn post", type= "list") | |
| response_schema = [ | |
| keywords, | |
| Take_aways, | |
| Highlights | |
| ] | |
| output_parser = StructuredOutputParser.from_response_schemas(response_schema) | |
| format_instructions = output_parser.get_format_instructions() | |
| template = """ | |
| You are a helpful keywords , take aways and highlights extractor from the post of LinkedIn Bot. Your task is to extract relevant keywords , take aways and highlights in descending order of their scores in a list, means high relevant should be on the top . | |
| From the following text message, extract the following information: | |
| text message: {content} | |
| {format_instructions} | |
| """ | |
| prompt_template = ChatPromptTemplate.from_template(template) | |
| messages = prompt_template.format_messages(content=post_data, format_instructions=format_instructions) | |
| response = model(messages) | |
| output_dict= output_parser.parse(response.content) | |
| return output_dict |