first change

main.py

@@ -0,0 +1,104 @@
+import streamlit as st
+import faiss
+import numpy as np
+import os
+import pandas as pd
+from dotenv import load_dotenv
+from sentence_transformers import SentenceTransformer
+from langchain_community.vectorstores import FAISS
+from langchain_huggingface import HuggingFaceEmbeddings
+from groq import Groq
+
+
+
+class JobRecommender:
+    def __init__(self, data_path: str, faiss_index_path: str, embeddings_path: str):
+        """Initialize the job recommender system."""
+        load_dotenv()
+        self.client = Groq(api_key=os.getenv("GROQ_API_KEY"))
+        self.embedding_model = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+        self.data_path = data_path
+        self.faiss_index_path = faiss_index_path
+        self.embeddings_path = embeddings_path
+        self.df = self._load_data()
+        self.faiss_index, self.job_metadata = self._load_or_build_faiss_index()
+    
+    def _load_data(self):
+        """Load job data from CSV."""
+        df = pd.read_csv(self.data_path).head(5000)
+        return df
+    
+    def _load_or_build_faiss_index(self):
+        """Load precomputed FAISS index or build it if it doesn't exist."""
+        if os.path.exists(self.faiss_index_path) and os.path.exists(self.embeddings_path):
+            print("Loading precomputed FAISS index and embeddings.")
+            faiss_index = faiss.read_index(self.faiss_index_path)
+            job_embeddings = np.load(self.embeddings_path)
+            job_metadata = {i: self.df.iloc[i].to_dict() for i in range(len(self.df))}
+        else:
+            print("Building FAISS index and embeddings.")
+            job_texts = self.df.apply(lambda row: f"{row['Job Title']} - {row['Job Description']}", axis=1).tolist()
+            job_embeddings = self.embedding_model.embed_documents(job_texts)
+            dimension = len(job_embeddings[0])
+            faiss_index = faiss.IndexFlatL2(dimension)
+            faiss_index.add(np.array(job_embeddings))
+            # Save the FAISS index and embeddings
+            faiss.write_index(faiss_index, self.faiss_index_path)
+            np.save(self.embeddings_path, np.array(job_embeddings))
+            job_metadata = {i: self.df.iloc[i].to_dict() for i in range(len(self.df))}
+        return faiss_index, job_metadata
+    
+    def find_similar_jobs(self, query: str, top_k=3):
+        """Retrieve similar jobs using FAISS."""
+        query_embedding = np.array([self.embedding_model.embed_query(query)])
+        distances, indices = self.faiss_index.search(query_embedding, top_k)
+        return [self.job_metadata[idx] for idx in indices[0]]
+    
+    def generate_response(self, user_query: str):
+        """Generate AI-powered job recommendations using Groq API."""
+        jobs = self.find_similar_jobs(user_query)
+        if not jobs:
+            return "No matching jobs found."
+        
+        job_details = "\n".join([f"{job['Job Title']}: {job['Job Description']}" for job in jobs])
+        prompt = f"""
+        You are a job recommendation assistant. A user is looking for a job related to: {user_query}.
+        Here are some recommended jobs:
+        {job_details}
+        Provide a detailed recommendation with insights on why these jobs are relevant.
+        """
+        
+        completion = self.client.chat.completions.create(
+            model="mixtral-8x7b-32768",
+            messages=[{"role": "user", "content": prompt}],
+            temperature=1,
+            max_tokens=1024,
+            top_p=1,
+            stream=True,
+        )
+        
+        response_text = "".join(chunk.choices[0].delta.content or "" for chunk in completion)
+        return response_text
+
+# Streamlit UI
+def main():
+    st.title("💼 Job Recommendation Chatbot")
+    st.write("Enter your job preferences below, and the AI will suggest relevant jobs!")
+    
+    recommender = JobRecommender(
+        data_path="job_desc.csv",
+        faiss_index_path="faiss_index.index",
+        embeddings_path="job_embeddings.npy"
+    )
+    user_input = st.text_input("Enter job title, skills, or interests:", "")
+    
+    if st.button("Find Jobs"):
+        if user_input:
+            response = recommender.generate_response(user_input)
+            st.subheader("📌 Job Recommendations")
+            st.write(response)
+        else:
+            st.warning("Please enter a job-related query.")
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,116 @@
+aiohappyeyeballs==2.4.6
+aiohttp==3.11.13
+aiosignal==1.3.2
+altair==5.5.0
+annotated-types==0.7.0
+anyio==4.8.0
+async-timeout==4.0.3
+attrs==25.1.0
+blinker==1.9.0
+cachetools==5.5.2
+certifi==2025.1.31
+charset-normalizer==3.4.1
+click==8.1.8
+dataclasses-json==0.6.7
+distro==1.9.0
+exceptiongroup==1.2.2
+faiss-cpu==1.10.0
+filelock==3.17.0
+frozenlist==1.5.0
+fsspec==2025.2.0
+gitdb==4.0.12
+GitPython==3.1.44
+greenlet==3.1.1
+groq==0.18.0
+h11==0.14.0
+httpcore==1.0.7
+httpx==0.28.1
+httpx-sse==0.4.0
+huggingface-hub==0.29.1
+idna==3.10
+Jinja2==3.1.5
+joblib==1.4.2
+jsonpatch==1.33
+jsonpointer==3.0.0
+jsonschema==4.23.0
+jsonschema-specifications==2024.10.1
+langchain==0.3.19
+langchain-community==0.3.18
+langchain-core==0.3.40
+langchain-huggingface==0.1.2
+langchain-text-splitters==0.3.6
+langsmith==0.3.11
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+marshmallow==3.26.1
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.1.0
+mypy-extensions==1.0.0
+narwhals==1.28.0
+nest-asyncio==1.6.0
+networkx==3.4.2
+numpy==1.26.4
+nvidia-cublas-cu12==12.4.5.8
+nvidia-cuda-cupti-cu12==12.4.127
+nvidia-cuda-nvrtc-cu12==12.4.127
+nvidia-cuda-runtime-cu12==12.4.127
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.2.1.3
+nvidia-curand-cu12==10.3.5.147
+nvidia-cusolver-cu12==11.6.1.9
+nvidia-cusparse-cu12==12.3.1.170
+nvidia-cusparselt-cu12==0.6.2
+nvidia-nccl-cu12==2.21.5
+nvidia-nvjitlink-cu12==12.4.127
+nvidia-nvtx-cu12==12.4.127
+orjson==3.10.15
+packaging==24.2
+pandas==2.2.3
+pillow==11.1.0
+propcache==0.3.0
+protobuf==5.29.3
+pyarrow==19.0.1
+pydantic==2.10.6
+pydantic-settings==2.8.0
+pydantic_core==2.27.2
+pydeck==0.9.1
+Pygments==2.19.1
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+pytz==2025.1
+PyYAML==6.0.2
+referencing==0.36.2
+regex==2024.11.6
+requests==2.32.3
+requests-toolbelt==1.0.0
+rich==13.9.4
+rpds-py==0.23.1
+safetensors==0.5.3
+scikit-learn==1.6.1
+scipy==1.15.2
+sentence-transformers==3.4.1
+six==1.17.0
+smmap==5.0.2
+sniffio==1.3.1
+SQLAlchemy==2.0.38
+streamlit==1.42.2
+sympy==1.13.1
+tenacity==9.0.0
+threadpoolctl==3.5.0
+tokenizers==0.21.0
+toml==0.10.2
+torch==2.6.0
+torchaudio==2.6.0
+torchvision==0.21.0
+tornado==6.4.2
+tqdm==4.67.1
+transformers==4.49.0
+triton==3.2.0
+typing-inspect==0.9.0
+typing_extensions==4.12.2
+tzdata==2025.1
+urllib3==2.3.0
+watchdog==6.0.0
+yarl==1.18.3
+zstandard==0.23.0