Spaces:
Build error
Build error
Download utils.py from vmalapaka/Resume_Screening: direct link, hf CLI and curl.
- Browser
- Download file 2.6 kB
-
https://huggingface.co/spaces/vmalapaka/Resume_Screening/resolve/main/utils.py
- Command line
-
hf download hf://spaces/vmalapaka/Resume_Screening/utils.py
-
curl -L -o utils.py https://huggingface.co/spaces/vmalapaka/Resume_Screening/resolve/main/utils.py
2.6 kB
| from langchain.vectorstores import Pinecone | |
| from langchain.llms import OpenAI | |
| from langchain.embeddings.sentence_transformer import SentenceTransformerEmbeddings | |
| from langchain.schema import Document | |
| import pinecone | |
| from pypdf import PdfReader | |
| from langchain.llms.openai import OpenAI | |
| from langchain.chains.summarize import load_summarize_chain | |
| from langchain_community.llms import HuggingFaceHub | |
| import time | |
| def get_pdf_text(pdf_doc): | |
| text = "" | |
| pdf_reader = PdfReader(pdf_doc) | |
| for page in pdf_reader.pages: | |
| text += page.extract_text() | |
| return text | |
| def create_docs(user_pdf_list, unique_id): | |
| docs=[] | |
| for filename in user_pdf_list: | |
| chunks=get_pdf_text(filename) | |
| #Adding items to our list - Adding data & its metadata | |
| docs.append(Document( | |
| page_content=chunks, | |
| metadata={"name": filename.name,"id":filename.file_id,"type=":filename.type,"size":filename.size,"unique_id":unique_id}, | |
| )) | |
| return docs | |
| def create_embeddings_load_data(): | |
| embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2") | |
| return embeddings | |
| #Function to push data to Vector Store - Pinecone here | |
| def push_to_pinecone(pinecone_apikey,pinecone_environment,pinecone_index_name,embeddings,docs): | |
| pinecone.init( | |
| api_key=pinecone_apikey, | |
| environment=pinecone_environment | |
| ) | |
| Pinecone.from_documents(docs, embeddings, index_name=pinecone_index_name) | |
| #Function to pull infrmation from Vector Store - Pinecone here | |
| def pull_from_pinecone(pinecone_apikey,pinecone_environment,pinecone_index_name,embeddings): | |
| time.sleep(20) | |
| pinecone.init( | |
| api_key=pinecone_apikey, | |
| environment=pinecone_environment | |
| ) | |
| index_name = pinecone_index_name | |
| index = Pinecone.from_existing_index(index_name, embeddings) | |
| return index | |
| #Function to help us get relavant documents from vector store - based on user input | |
| def similar_docs(query,k,pinecone_apikey,pinecone_environment,pinecone_index_name,embeddings,unique_id): | |
| pinecone.init( | |
| api_key=pinecone_apikey, | |
| environment=pinecone_environment | |
| ) | |
| index_name = pinecone_index_name | |
| index = pull_from_pinecone(pinecone_apikey,pinecone_environment,index_name,embeddings) | |
| similar_docs = index.similarity_search_with_score(query, int(k),{"unique_id":unique_id}) | |
| return similar_docs | |
| # Summary of a document | |
| def get_summary(current_doc): | |
| llm = OpenAI(temperature=0) | |
| chain = load_summarize_chain(llm, chain_type="map_reduce") | |
| summary = chain.run([current_doc]) | |
| return summary |