# Import necessary libraries import os import pandas as pd from sentence_transformers import SentenceTransformer import faiss import numpy as np import gradio as gr from groq import Groq # Set up Groq API GROQ_API_KEY = "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" # Replace with your Groq API key client = Groq(api_key=GROQ_API_KEY) # Load environmental data (replace 'dataset.csv' with your actual file path) df = pd.read_csv('./environmental_impact_assessment_dataset.csv') # Path to your uploaded dataset # Combine text columns relevant to the project for embedding (adjust as per your dataset) text_column = df['Project Type'] + ' ' + df['Mitigation Measures'] # Example of combining fields # Use SentenceTransformer for embeddings (lighter and no API key required) embedding_model = SentenceTransformer('all-MiniLM-L6-v2') # A lighter sentence transformer model # Generate embeddings for the texts embeddings = embedding_model.encode(text_column.tolist()) # Convert embeddings to a numpy array for FAISS embeddings_np = np.array(embeddings).astype(np.float32) # Build the FAISS index index = faiss.IndexFlatL2(embeddings_np.shape[1]) # Create the index (L2 distance) index.add(embeddings_np) # Add embeddings to the index # Function to perform search and retrieval from FAISS def retrieve_relevant_document(query): query_embedding = embedding_model.encode([query]) # Generate embedding for the query query_embedding_np = np.array(query_embedding).astype(np.float32) # Convert to numpy array # Perform similarity search in the FAISS index _, indices = index.search(query_embedding_np, k=1) # Get the top 1 most similar document retrieved_text = text_column.iloc[indices[0][0]] # Get the corresponding text return retrieved_text # Function to generate a report using the Groq API def generate_report(user_input): # Handle cases where the user input is empty if not user_input.strip(): return "Please provide project details to generate an Environmental Impact Assessment (EIA) report." # Retrieve the relevant document from FAISS relevant_document = retrieve_relevant_document(user_input) # Use Groq API to generate the response based on the retrieved document chat_completion = client.chat.completions.create( messages=[ {"role": "user", "content": f"Generate an environmental impact assessment report based on the following project details:\n\n{relevant_document}\n\nUser query: {user_input}"} ], model="llama3-8b-8192", # Use a suitable model from Groq ) return chat_completion.choices[0].message.content # Define the Gradio interface for user input and output def gradio_interface(project_details): # Call the report generation function and return the output return generate_report(project_details) # Set up Gradio UI iface = gr.Interface( fn=gradio_interface, inputs="text", # Textbox input for project details outputs="text", # Text output for the generated report live=False # Set live to False for better user experience ) # Launch the Gradio interface iface.launch()