Spaces:
Running
Running
File size: 2,805 Bytes
4025ad0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 |
from langchain_groq import ChatGroq
from langchain_community.document_loaders import PyPDFLoader, UnstructuredWordDocumentLoader, TextLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores import FAISS
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
import os
from dotenv import load_dotenv
load_dotenv()
def load_resume(file_path):
"""Load resume from PDF, DOCX, or TXT"""
if file_path.endswith('.pdf'):
loader = PyPDFLoader(file_path)
elif file_path.endswith('.docx'):
loader = UnstructuredWordDocumentLoader(file_path)
elif file_path.endswith('.txt'):
loader = TextLoader(file_path)
else:
raise ValueError("Supported formats: PDF, DOCX, TXT")
return loader.load()
def create_resume_qa_system(resume_file_path):
"""Create complete resume Q&A system"""
# 1. Load and split resume
docs = load_resume(resume_file_path)
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=800,
chunk_overlap=100
)
splits = text_splitter.split_documents(docs)
# 2. Create embeddings and vector store
embeddings = HuggingFaceEmbeddings(
model_name="sentence-transformers/all-MiniLM-L6-v2"
)
vectorstore = FAISS.from_documents(splits, embeddings)
# 3. Setup LLM
llm = ChatGroq(
api_key=os.getenv('GROQ_API_KEY'),
model=os.getenv('GROQ_MODEL', 'llama-3.1-8b-instant'),
temperature=0.1
)
# 4. Retrieval chain
retriever = vectorstore.as_retriever(search_kwargs={"k": 4})
template = """Use the following resume context to answer the question.
If you don't know the answer, say so. Answer concisely and accurately.
Context: {context}
Question: {question}
Answer:"""
prompt = ChatPromptTemplate.from_template(template)
def format_docs(docs):
return "\n\n".join(doc.page_content for doc in docs)
chain = (
{"context": retriever | format_docs, "question": RunnablePassthrough()}
| prompt
| llm
| StrOutputParser()
)
return chain
# Usage
if __name__ == "__main__":
# Replace with your resume path
qa_chain = create_resume_qa_system("path/to/your/resume.pdf")
# Ask questions
questions = [
"What is my experience with Microsoft Fabric?",
"List my technical skills",
"What certifications do I have?",
"Describe my Databricks projects"
]
for question in questions:
answer = qa_chain.invoke(question)
print(f"Q: {question}\nA: {answer}\n{'-' * 50}")
|