| # import streamlit as st | |
| # import os | |
| # import pandas as pd | |
| # import random | |
| # from os.path import join | |
| # from src import preprocess_and_load_df, load_agent, ask_agent, decorate_with_code, show_response, get_from_user, load_smart_df, ask_question | |
| # from dotenv import load_dotenv | |
| # from langchain_groq.chat_models import ChatGroq | |
| # load_dotenv("Groq.txt") | |
| # Groq_Token = os.environ["GROQ_API_KEY"] | |
| # models = {"llama3":"llama3-70b-8192","mixtral": "mixtral-8x7b-32768", "llama2": "llama2-70b-4096", "gemma": "gemma-7b-it"} | |
| # self_path = os.path.dirname(os.path.abspath(__file__)) | |
| # # Using HTML and CSS to center the title | |
| # st.write( | |
| # """ | |
| # <style> | |
| # .title { | |
| # text-align: center; | |
| # color: #17becf; | |
| # } | |
| # """, | |
| # unsafe_allow_html=True, | |
| # ) | |
| # # Displaying the centered title | |
| # st.markdown("<h2 class='title'>VayuBuddy</h2>", unsafe_allow_html=True) | |
| # st.markdown("<div style='text-align:center; padding: 20px;'>VayuBuddy makes pollution monitoring easier by bridging the gap between users and datasets.<br>No coding required—just meaningful insights at your fingertips!</div>", unsafe_allow_html=True) | |
| # # Center-aligned instruction text with bold formatting | |
| # st.markdown("<div style='text-align:center;'>Choose a query from <b>Select a prompt</b> or type a query in the <b>chat box</b>, select a <b>LLM</b> (Large Language Model), and press enter to generate a response.</div>", unsafe_allow_html=True) | |
| # # os.environ["PANDASAI_API_KEY"] = "$2a$10$gbmqKotzJOnqa7iYOun8eO50TxMD/6Zw1pLI2JEoqncwsNx4XeBS2" | |
| # # with open(join(self_path, "context1.txt")) as f: | |
| # # context = f.read().strip() | |
| # # agent = load_agent(join(self_path, "app_trial_1.csv"), context) | |
| # # df = preprocess_and_load_df(join(self_path, "Data.csv")) | |
| # # inference_server = "https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2" | |
| # # inference_server = "https://api-inference.huggingface.co/models/codellama/CodeLlama-13b-hf" | |
| # # inference_server = "https://api-inference.huggingface.co/models/pandasai/bamboo-llm" | |
| # model_name = st.sidebar.selectbox("Select LLM:", ["llama3","mixtral", "gemma"]) | |
| # questions = ('Custom Prompt', | |
| # 'Plot the monthly average PM2.5 for the year 2023.', | |
| # 'Which month in which year has the highest average PM2.5 overall?', | |
| # 'Which month in which year has the highest PM2.5 overall?', | |
| # 'Which month has the highest average PM2.5 in 2023 for Mumbai?', | |
| # 'Plot and compare monthly timeseries of pollution for Mumbai and Bengaluru.', | |
| # 'Plot the yearly average PM2.5.', | |
| # 'Plot the monthly average PM2.5 of Delhi, Mumbai and Bengaluru for the year 2022.', | |
| # 'Which month has the highest pollution?', | |
| # 'Which city has the highest PM2.5 level in July 2022?', | |
| # 'Plot and compare monthly timeseries of PM2.5 for Mumbai and Bengaluru.', | |
| # 'Plot and compare the monthly average PM2.5 of Delhi, Mumbai and Bengaluru for the year 2022.', | |
| # 'Plot the monthly average PM2.5.', | |
| # 'Plot the monthly average PM10 for the year 2023.', | |
| # 'Which (month, year) has the highest PM2.5?', | |
| # 'Plot the monthly average PM2.5 of Delhi for the year 2022.', | |
| # 'Plot the monthly average PM2.5 of Bengaluru for the year 2022.', | |
| # 'Plot the monthly average PM2.5 of Mumbai for the year 2022.', | |
| # 'Which state has the highest average PM2.5?', | |
| # 'Plot monthly PM2.5 in Gujarat for 2023.', | |
| # 'What is the name of the month with the highest average PM2.5 overall?') | |
| # waiting_lines = ("Thinking...", "Just a moment...", "Let me think...", "Working on it...", "Processing...", "Hold on...", "One moment...", "On it...") | |
| # # agent = load_agent(df, context="", inference_server=inference_server, name=model_name) | |
| # # Initialize chat history | |
| # if "responses" not in st.session_state: | |
| # st.session_state.responses = [] | |
| # # Display chat responses from history on app rerun | |
| # for response in st.session_state.responses: | |
| # if not response["no_response"]: | |
| # show_response(st, response) | |
| # show = True | |
| # if prompt := st.sidebar.selectbox("Select a Prompt:", questions): | |
| # # add a note "select custom prompt to ask your own question" | |
| # st.sidebar.info("Select 'Custom Prompt' to ask your own question.") | |
| # if prompt == 'Custom Prompt': | |
| # show = False | |
| # # React to user input | |
| # prompt = st.chat_input("Ask me anything about air quality!", key=10) | |
| # if prompt : show = True | |
| # if show : | |
| # # Add user input to chat history | |
| # response = get_from_user(prompt) | |
| # response["no_response"] = False | |
| # st.session_state.responses.append(response) | |
| # # Display user input | |
| # show_response(st, response) | |
| # no_response = False | |
| # # select random waiting line | |
| # with st.spinner(random.choice(waiting_lines)): | |
| # ran = False | |
| # for i in range(1): | |
| # print(f"Attempt {i+1}") | |
| # llm = ChatGroq(model=models[model_name], api_key=os.getenv("GROQ_API"), temperature=0) | |
| # df_check = pd.read_csv("Data.csv") | |
| # df_check["Timestamp"] = pd.to_datetime(df_check["Timestamp"]) | |
| # df_check = df_check.head(5) | |
| # new_line = "\n" | |
| # parameters = {"font.size": 12} | |
| # template = f"""```python | |
| # import pandas as pd | |
| # import matplotlib.pyplot as plt | |
| # # plt.rcParams.update({parameters}) | |
| # df = pd.read_csv("Data.csv") | |
| # df["Timestamp"] = pd.to_datetime(df["Timestamp"]) | |
| # import geopandas as gpd | |
| # india = gpd.read_file("https://gist.githubusercontent.com/jbrobst/56c13bbbf9d97d187fea01ca62ea5112/raw/e388c4cae20aa53cb5090210a42ebb9b765c0a36/india_states.geojson") | |
| # india.loc[india['ST_NM'].isin(['Ladakh', 'Jammu & Kashmir']), 'ST_NM'] = 'Jammu and Kashmir' | |
| # # df.dtypes | |
| # {new_line.join(map(lambda x: '# '+x, str(df_check.dtypes).split(new_line)))} | |
| # # {prompt.strip()} | |
| # # <your code here> | |
| # ``` | |
| # """ | |
| # query = f"""I have a pandas dataframe data of PM2.5 and PM10. | |
| # * The columns are 'Timestamp', 'station', 'PM2.5', 'PM10', 'address', 'city', 'latitude', 'longitude',and 'state'. | |
| # * Frequency of data is daily. | |
| # * `pollution` generally means `PM2.5`. | |
| # * You already have df, so don't read the csv file | |
| # * Don't print anything, but save result in a variable `answer` and make it global. | |
| # * Unless explicitly mentioned, don't consider the result as a plot. | |
| # * PM2.5 guidelines: India: 60, WHO: 15. | |
| # * PM10 guidelines: India: 100, WHO: 50. | |
| # * If result is a plot, show the India and WHO guidelines in the plot. | |
| # * If result is a plot make it in tight layout, save it and save path in `answer`. Example: `answer='plot.png'` | |
| # * If result is a plot, rotate x-axis tick labels by 45 degrees, | |
| # * If result is not a plot, save it as a string in `answer`. Example: `answer='The city is Mumbai'` | |
| # * I have a geopandas.geodataframe india containining the coordinates required to plot Indian Map with states. | |
| # * If the query asks you to plot on India Map, use that geodataframe to plot and then add more points as per the requirements using the similar code as follows : v = ax.scatter(df['longitude'], df['latitude']). If the colorbar is required, use the following code : plt.colorbar(v) | |
| # * If the query asks you to plot on India Map plot the India Map in Beige color | |
| # * Whenever you do any sort of aggregation, report the corresponding standard deviation, standard error and the number of data points for that aggregation. | |
| # * Whenever you're reporting a floating point number, round it to 2 decimal places. | |
| # * Always report the unit of the data. Example: `The average PM2.5 is 45.67 µg/m³` | |
| # Complete the following code. | |
| # {template} | |
| # """ | |
| # answer = None | |
| # code = None | |
| # try: | |
| # answer = llm.invoke(query) | |
| # code = f""" | |
| # {template.split("```python")[1].split("```")[0]} | |
| # {answer.content.split("```python")[1].split("```")[0]} | |
| # """ | |
| # # update variable `answer` when code is executed | |
| # exec(code) | |
| # ran = True | |
| # no_response = False | |
| # except Exception as e: | |
| # no_response = True | |
| # exception = e | |
| # if code is not None: | |
| # answer = f"!!!Faced an error while working on your query. Please try again!!!" | |
| # if type(answer) != str: | |
| # answer = f"!!!Faced an error while working on your query. Please try again!!!" | |
| # response = {"role": "assistant", "content": answer, "gen_code": code, "ex_code": code, "last_prompt": prompt, "no_response": no_response} | |
| # # Get response from agent | |
| # # response = ask_question(model_name=model_name, question=prompt) | |
| # # response = ask_agent(agent, prompt) | |
| # if ran: | |
| # break | |
| # # Display agent response | |
| # if code is not None: | |
| # # Add agent response to chat history | |
| # print("Adding response") | |
| # st.session_state.responses.append(response) | |
| # show_response(st, response) | |
| # if no_response: | |
| # print("No response") | |
| # st.error(f"Failed to generate right output due to the following error:\n\n{exception}") | |
| # prompt = 'Custom Prompt' | |
| ####################################################Added User Feedback################################################### | |
| import streamlit as st | |
| import os | |
| import pandas as pd | |
| import random | |
| from os.path import join | |
| from src import preprocess_and_load_df, load_agent, ask_agent, decorate_with_code, show_response, get_from_user, load_smart_df, ask_question | |
| from dotenv import load_dotenv | |
| from langchain_groq.chat_models import ChatGroq | |
| from datasets import Dataset, load_dataset, concatenate_datasets | |
| import streamlit as st | |
| from streamlit_feedback import streamlit_feedback | |
| import uuid | |
| from huggingface_hub import login, HfFolder | |
| import os | |
| # Set the token | |
| token = os.getenv("HF_TOKEN") # Replace "YOUR_AUTHENTICATION_TOKEN" with your actual token | |
| # Login using the token | |
| login(token=token) | |
| model_name = st.sidebar.selectbox("Select LLM:", ["llama3","mixtral", "gemma"]) | |
| contact_details = """ | |
| **Feel free to reach out to us:** | |
| - [Nipun Batra](mailto:[email protected]) | |
| - [Zeel B Patel](mailto:[email protected]) | |
| - [Yash J Bachwana](mailto:[email protected]) | |
| """ | |
| for _ in range(12): | |
| st.sidebar.markdown(" ") | |
| # Display contact details with message | |
| st.sidebar.markdown("<hr>", unsafe_allow_html=True) | |
| st.sidebar.markdown(contact_details, unsafe_allow_html=True) | |
| # Function to push feedback data to Hugging Face Hub dataset | |
| def push_to_dataset(feedback, comments,output,code,error): | |
| # Load existing dataset or create a new one if it doesn't exist | |
| try: | |
| ds = load_dataset("YashB1/Feedbacks_eoc", split="evaluation") | |
| except FileNotFoundError: | |
| # If dataset doesn't exist, create a new one | |
| ds = Dataset.from_dict({"feedback": [], "comments": [], "error": [], "output": [], "code": []}) | |
| # Add new feedback to the dataset | |
| new_data = {"feedback": [feedback], "comments": [comments], "error": [error], "output": [output], "code": [code]} # Convert feedback and comments to lists | |
| new_data = Dataset.from_dict(new_data) | |
| ds = concatenate_datasets([ds, new_data]) | |
| # Push the updated dataset to Hugging Face Hub | |
| ds.push_to_hub("YashB1/Feedbacks_eoc", split="evaluation") | |
| load_dotenv("Groq.txt") | |
| Groq_Token = os.environ["GROQ_API_KEY"] | |
| models = {"llama3":"llama3-70b-8192","mixtral": "mixtral-8x7b-32768", "llama2": "llama2-70b-4096", "gemma": "gemma-7b-it"} | |
| self_path = os.path.dirname(os.path.abspath(__file__)) | |
| # Using HTML and CSS to center the title | |
| st.write( | |
| """ | |
| <style> | |
| .title { | |
| text-align: center; | |
| color: #17becf; | |
| } | |
| """, | |
| unsafe_allow_html=True, | |
| ) | |
| # Displaying the centered title | |
| st.markdown("<h2 class='title'>VayuBuddy</h2>", unsafe_allow_html=True) | |
| st.markdown("<div style='text-align:center; padding: 20px;'>VayuBuddy makes pollution monitoring easier by bridging the gap between users and datasets.<br>No coding required—just meaningful insights at your fingertips!</div>", unsafe_allow_html=True) | |
| # Center-aligned instruction text with bold formatting | |
| st.markdown("<div style='text-align:center;'>Choose a query from <b>Select a prompt</b> or type a query in the <b>chat box</b>, select a <b>LLM</b> (Large Language Model), and press enter to generate a response.</div>", unsafe_allow_html=True) | |
| # os.environ["PANDASAI_API_KEY"] = "$2a$10$gbmqKotzJOnqa7iYOun8eO50TxMD/6Zw1pLI2JEoqncwsNx4XeBS2" | |
| # with open(join(self_path, "context1.txt")) as f: | |
| # context = f.read().strip() | |
| # agent = load_agent(join(self_path, "app_trial_1.csv"), context) | |
| # df = preprocess_and_load_df(join(self_path, "Data.csv")) | |
| # inference_server = "https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2" | |
| # inference_server = "https://api-inference.huggingface.co/models/codellama/CodeLlama-13b-hf" | |
| # inference_server = "https://api-inference.huggingface.co/models/pandasai/bamboo-llm" | |
| # model_name = st.sidebar.selectbox("Select LLM:", ["llama3","mixtral", "gemma"]) | |
| if 'question_state' not in st.session_state: | |
| st.session_state.question_state = False | |
| if 'fbk' not in st.session_state: | |
| st.session_state.fbk = str(uuid.uuid4()) | |
| if 'feedback' not in st.session_state: | |
| st.session_state.feedback = None | |
| if "chat_history" not in st.session_state: | |
| st.session_state.chat_history = [] | |
| def display_answer(): | |
| for entry in st.session_state.chat_history: | |
| with st.chat_message("human"): | |
| st.write(entry["question"]) | |
| # st.write(entry["answer"]) | |
| # print(entry["answer"]) | |
| show_response(st, entry["answer"]) | |
| def fbcb(response): | |
| """Update the history with feedback. | |
| The question and answer are already saved in history. | |
| Now we will add the feedback in that history entry. | |
| """ | |
| display_answer() # display hist | |
| # Create a new feedback by changing the key of feedback component. | |
| st.session_state.fbk = str(uuid.uuid4()) | |
| question = st.chat_input(placeholder="Ask your question here .... !!!!") | |
| if question: | |
| # We need this because of feedback. That question above | |
| # is a stopper. If user hits the feedback button, streamlit | |
| # reruns the code from top and we cannot enter back because | |
| # of that chat_input. | |
| st.session_state.prompt = question | |
| st.session_state.question_state = True | |
| # We are now free because st.session_state.question_state is True. | |
| # But there are consequences. We will have to handle | |
| # the double runs of create_answer() and display_answer() | |
| # just to get the user feedback. | |
| if st.session_state.question_state: | |
| waiting_lines = ("Thinking...", "Just a moment...", "Let me think...", "Working on it...", "Processing...", "Hold on...", "One moment...", "On it...") | |
| with st.spinner(random.choice(waiting_lines)): | |
| ran = False | |
| for i in range(5): | |
| print(f"Attempt {i+1}") | |
| llm = ChatGroq(model=models[model_name], api_key=os.getenv("GROQ_API"), temperature=0) | |
| df_check = pd.read_csv("Data.csv") | |
| df_check["Timestamp"] = pd.to_datetime(df_check["Timestamp"]) | |
| df_check = df_check.head(5) | |
| new_line = "\n" | |
| parameters = {"font.size": 12} | |
| # If the query asks you to make a gif/animation, don't use savefig to save it. Instead use ani.save(answer, writer='pillow'). | |
| # If the query asks you to make a gif/animation, don't use colormaps . | |
| template = f"""```python | |
| import pandas as pd | |
| import matplotlib.pyplot as plt | |
| # plt.rcParams.update({parameters}) | |
| df = pd.read_csv("Data.csv") | |
| df["Timestamp"] = pd.to_datetime(df["Timestamp"]) | |
| import geopandas as gpd | |
| file_path = "india_states.geojson" | |
| india = gpd.read_file("https://gist.githubusercontent.com/jbrobst/56c13bbbf9d97d187fea01ca62ea5112/raw/e388c4cae20aa53cb5090210a42ebb9b765c0a36/india_states.geojson") | |
| india.loc[india['ST_NM'].isin(['Ladakh', 'Jammu & Kashmir']), 'ST_NM'] = 'Jammu and Kashmir' | |
| # df.dtypes | |
| {new_line.join(map(lambda x: '# '+x, str(df_check.dtypes).split(new_line)))} | |
| # {st.session_state.prompt.strip()} | |
| # <your code here> | |
| ``` | |
| """ | |
| query = f"""I have a pandas dataframe data of PM2.5 and PM10. | |
| * The columns are 'Timestamp', 'station', 'PM2.5', 'PM10', 'address', 'city', 'latitude', 'longitude',and 'state'. | |
| * Frequency of data is daily. | |
| * `pollution` generally means `PM2.5`. | |
| * You already have df, so don't read the csv file | |
| * Don't print anything, but save result in a variable `answer` and make it global. | |
| * Unless explicitly mentioned, don't consider the result as a plot. | |
| * PM2.5 guidelines: India: 60, WHO: 15. | |
| * PM10 guidelines: India: 100, WHO: 50. | |
| * If query asks to plot calendarmap, use library calmap. | |
| * If result is a plot, show the India and WHO guidelines in the plot. | |
| * If result is a plot make it in tight layout, save it and save path in `answer`. Example: `answer='plot.png'` | |
| * If result is a plot, rotate x-axis tick labels by 45 degrees, | |
| * If result is not a plot, save it as a string in `answer`. Example: `answer='The city is Mumbai'` | |
| * I have a geopandas.geodataframe india containining the coordinates required to plot Indian Map with states. | |
| * If the query asks you to plot on India Map, use that geodataframe to plot and then add more points as per the requirements using the similar code as follows : v = ax.scatter(df['longitude'], df['latitude']). If the colorbar is required, use the following code : plt.colorbar(v) | |
| * If the query asks you to plot on India Map plot the India Map in Beige color | |
| * Whenever you do any sort of aggregation, report the corresponding standard deviation, standard error and the number of data points for that aggregation. | |
| * Whenever you're reporting a floating point number, round it to 2 decimal places. | |
| * Always report the unit of the data. Example: `The average PM2.5 is 45.67 µg/m³` | |
| Complete the following code. | |
| {template} | |
| """ | |
| answer = None | |
| code = None | |
| exception = None | |
| try: | |
| answer = llm.invoke(query) | |
| code = f""" | |
| {template.split("```python")[1].split("```")[0]} | |
| {answer.content.split("```python")[1].split("```")[0]} | |
| """ | |
| # update variable `answer` when code is executed | |
| exec(code) | |
| ran = True | |
| no_response = False | |
| except Exception as e: | |
| no_response = True | |
| exception = e | |
| if code is not None: | |
| answer = f"!!!Faced an error while working on your query. Please try again!!!" | |
| if type(answer) != str: | |
| answer = f"!!!Faced an error while working on your query. Please try again!!!" | |
| response = {"role": "assistant", "content": answer, "gen_code": code, "ex_code": code, "last_prompt": st.session_state.prompt, "no_response": no_response,"exception": exception} | |
| # print(response) | |
| if ran: | |
| break | |
| # Display agent response | |
| if code is not None: | |
| # Add agent response to chat history | |
| if response['content'][-4:] == ".gif" : | |
| # Provide a button to show the gif, we don't want it to run forever | |
| st.image(response['content'], use_column_width=True) | |
| response['content'] = "" | |
| print("Adding response : ") | |
| message_id = len(st.session_state.chat_history) | |
| st.session_state.chat_history.append({ | |
| "question": st.session_state.prompt, | |
| "answer": response, | |
| "message_id": message_id, | |
| }) | |
| display_answer() | |
| if no_response: | |
| print("No response") | |
| st.error(f"Failed to generate right output due to the following error:\n\n{exception}") | |
| # display_answer() | |
| # Pressing a button in feedback reruns the code. | |
| st.session_state.feedback = streamlit_feedback( | |
| feedback_type="thumbs", | |
| optional_text_label="[Optional]", | |
| align="flex-start", | |
| key=st.session_state.fbk, | |
| on_submit=fbcb | |
| ) | |
| print("FeedBack",st.session_state.feedback) | |
| if st.session_state.feedback : | |
| push_to_dataset(st.session_state.feedback['score'],st.session_state.feedback['text'],answer,code,exception) | |
| st.success("Feedback submitted successfully!") | |