|
from flask import Flask, request |
|
from twilio.twiml.messaging_response import MessagingResponse |
|
from twilio.rest import Client |
|
import os |
|
import requests |
|
from PIL import Image |
|
import shutil |
|
|
|
from langchain.vectorstores.chroma import Chroma |
|
from langchain.prompts import ChatPromptTemplate |
|
from langchain_community.llms.ollama import Ollama |
|
from get_embedding_function import get_embedding_function |
|
from langchain.document_loaders.pdf import PyPDFDirectoryLoader |
|
from langchain_text_splitters import RecursiveCharacterTextSplitter |
|
from langchain.schema.document import Document |
|
|
|
app = Flask(__name__) |
|
UPLOAD_FOLDER = '/code/uploads' |
|
CHROMA_PATH = UPLOAD_FOLDER |
|
if not os.path.exists(UPLOAD_FOLDER): |
|
os.makedirs(UPLOAD_FOLDER) |
|
|
|
app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER |
|
|
|
class ConversationBufferMemory: |
|
def __init__(self, max_size=6): |
|
self.memory = [] |
|
self.max_size = max_size |
|
|
|
def add_to_memory(self, interaction): |
|
self.memory.append(interaction) |
|
if len(self.memory) > self.max_size: |
|
self.memory.pop(0) |
|
|
|
def get_memory(self): |
|
return self.memory |
|
|
|
conversation_memory = ConversationBufferMemory(max_size=2) |
|
|
|
account_sid = os.environ.get('TWILIO_ACCOUNT_SID') |
|
auth_token = os.environ.get('TWILIO_AUTH_TOKEN') |
|
client = Client(account_sid, auth_token) |
|
from_whatsapp_number = 'whatsapp:+14155238886' |
|
|
|
PROMPT_TEMPLATE = """ |
|
Answer the question based only on the following context: |
|
{context} |
|
--- |
|
Answer the question based on the above context: {question} |
|
""" |
|
|
|
from bs4 import BeautifulSoup |
|
import requests |
|
from requests.auth import HTTPBasicAuth |
|
from PIL import Image |
|
from io import BytesIO |
|
import pandas as pd |
|
from urllib.parse import urlparse |
|
import os |
|
from pypdf import PdfReader |
|
from ai71 import AI71 |
|
import uuid |
|
|
|
from inference_sdk import InferenceHTTPClient |
|
import base64 |
|
|
|
AI71_API_KEY = os.environ.get('AI71_API_KEY') |
|
|
|
def generate_response(query, chat_history): |
|
response = '' |
|
for chunk in AI71(AI71_API_KEY).chat.completions.create( |
|
model="tiiuae/falcon-180b-chat", |
|
messages=[ |
|
{"role": "system", "content": "You are the best agricultural assistant. Remember to give a response in not more than 2 sentences. Greet the user if the user greets you."}, |
|
{"role": "user", "content": f'''Answer the query based on history {chat_history}: {query}'''}, |
|
], |
|
stream=True, |
|
): |
|
if chunk.choices[0].delta.content: |
|
response += chunk.choices[0].delta.content |
|
return response.replace("###", '').replace('\nUser:', '') |
|
|
|
def predict_pest(filepath): |
|
CLIENT = InferenceHTTPClient( |
|
api_url="https://detect.roboflow.com", |
|
api_key="oF1aC4b1FBCDtK8CoKx7" |
|
) |
|
result = CLIENT.infer(filepath, model_id="pest-detection-ueoco/1") |
|
return result['predictions'][0] |
|
|
|
|
|
def predict_disease(filepath): |
|
CLIENT = InferenceHTTPClient( |
|
api_url="https://classify.roboflow.com", |
|
api_key="oF1aC4b1FBCDtK8CoKx7" |
|
) |
|
result = CLIENT.infer(filepath, model_id="plant-disease-detection-iefbi/1") |
|
return result['predicted_classes'][0] |
|
|
|
def convert_img(url, account_sid, auth_token): |
|
try: |
|
response = requests.get(url, auth=HTTPBasicAuth(account_sid, auth_token)) |
|
response.raise_for_status() |
|
|
|
parsed_url = urlparse(url) |
|
media_id = parsed_url.path.split('/')[-1] |
|
filename = f"downloaded_media_{media_id}" |
|
|
|
media_filepath = os.path.join(UPLOAD_FOLDER, filename) |
|
with open(media_filepath, 'wb') as file: |
|
file.write(response.content) |
|
|
|
print(f"Media downloaded successfully and saved as {media_filepath}") |
|
|
|
with open(media_filepath, 'rb') as img_file: |
|
image = Image.open(img_file) |
|
|
|
converted_filename = f"image.jpg" |
|
converted_filepath = os.path.join(UPLOAD_FOLDER, converted_filename) |
|
image.convert('RGB').save(converted_filepath, 'JPEG') |
|
return converted_filepath |
|
|
|
except requests.exceptions.HTTPError as err: |
|
print(f"HTTP error occurred: {err}") |
|
except Exception as err: |
|
print(f"An error occurred: {err}") |
|
|
|
def get_weather(city): |
|
city = city.strip().replace(' ', '+') |
|
r = requests.get(f'https://www.google.com/search?q=weather+in+{city}') |
|
soup = BeautifulSoup(r.text, 'html.parser') |
|
temperature = soup.find('div', attrs={'class': 'BNeawe iBp4i AP7Wnd'}).text |
|
return temperature |
|
|
|
from zenrows import ZenRowsClient |
|
Zenrow_api = os.environ.get('Zenrow_api') |
|
zenrows_client = ZenRowsClient(Zenrow_api) |
|
|
|
def get_rates(): |
|
url = "https://www.kisandeals.com/mandiprices/ALL/TAMIL-NADU/ALL" |
|
response = zenrows_client.get(url) |
|
|
|
if response.status_code == 200: |
|
soup = BeautifulSoup(response.content, 'html.parser') |
|
rows = soup.select('table tbody tr') |
|
data = {} |
|
for row in rows: |
|
columns = row.find_all('td') |
|
if len(columns) >= 2: |
|
commodity = columns[0].get_text(strip=True) |
|
price = columns[1].get_text(strip=True) |
|
if '₹' in price: |
|
data[commodity] = price |
|
return str(data) + " These are the prices for 1 kg" |
|
|
|
def get_news(): |
|
news = [] |
|
url = "https://economictimes.indiatimes.com/news/economy/agriculture?from=mdr" |
|
response = zenrows_client.get(url) |
|
|
|
if response.status_code == 200: |
|
soup = BeautifulSoup(response.content, 'html.parser') |
|
headlines = soup.find_all("div", class_="eachStory") |
|
for story in headlines: |
|
headline = story.find('h3').text.strip() |
|
news.append(headline) |
|
return news |
|
|
|
def download_and_save_as_txt(url, account_sid, auth_token): |
|
try: |
|
response = requests.get(url, auth=HTTPBasicAuth(account_sid, auth_token)) |
|
response.raise_for_status() |
|
|
|
parsed_url = urlparse(url) |
|
media_id = parsed_url.path.split('/')[-1] |
|
filename = f"pdf_file.pdf" |
|
|
|
txt_filepath = os.path.join(UPLOAD_FOLDER, filename) |
|
with open(txt_filepath, 'wb') as file: |
|
file.write(response.content) |
|
|
|
print(f"Media downloaded successfully and saved as {txt_filepath}") |
|
return txt_filepath |
|
|
|
except requests.exceptions.HTTPError as err: |
|
print(f"HTTP error occurred: {err}") |
|
except Exception as err: |
|
print(f"An error occurred: {err}") |
|
|
|
def query_rag(query_text: str): |
|
embedding_function = get_embedding_function() |
|
db = Chroma(persist_directory=CHROMA_PATH, embedding_function=embedding_function) |
|
results = db.similarity_search_with_score(query_text, k=5) |
|
context_text = "\n\n---\n\n".join([doc.page_content for doc, _score in results]) |
|
prompt_template = ChatPromptTemplate.from_template(PROMPT_TEMPLATE) |
|
prompt = prompt_template.format(context=context_text, question=query_text) |
|
model = Ollama(model="llama2") |
|
response_text = model.invoke(prompt) |
|
return response_text |
|
|
|
def save_pdf_and_update_database(media_url): |
|
response = requests.get(media_url) |
|
pdf_filename = os.path.join(UPLOAD_FOLDER, f"{uuid.uuid4()}.pdf") |
|
with open(pdf_filename, 'wb') as f: |
|
f.write(response.content) |
|
|
|
document_loader = PyPDFDirectoryLoader(UPLOAD_FOLDER) |
|
documents = document_loader.load() |
|
|
|
text_splitter = RecursiveCharacterTextSplitter( |
|
chunk_size=800, |
|
chunk_overlap=80, |
|
length_function=len, |
|
is_separator_regex=False, |
|
) |
|
chunks = text_splitter.split_documents(documents) |
|
|
|
add_to_chroma(chunks) |
|
|
|
def add_to_chroma(chunks: list[Document]): |
|
db = Chroma(persist_directory=CHROMA_PATH, embedding_function=get_embedding_function()) |
|
chunks_with_ids = calculate_chunk_ids(chunks) |
|
existing_items = db.get(include=[]) |
|
existing_ids = set(existing_items["ids"]) |
|
|
|
new_chunks = [chunk for chunk in chunks_with_ids if chunk.metadata["id"] not in existing_ids] |
|
|
|
if new_chunks: |
|
new_chunk_ids = [chunk.metadata["id"] for chunk in new_chunks] |
|
db.add_documents(new_chunks, ids=new_chunk_ids) |
|
db.persist() |
|
|
|
def calculate_chunk_ids(chunks): |
|
last_page_id = None |
|
current_chunk_index = 0 |
|
|
|
for chunk in chunks: |
|
source = chunk.metadata.get("source") |
|
page = chunk.metadata.get("page") |
|
current_page_id = f"{source}:{page}" |
|
|
|
if current_page_id == last_page_id: |
|
current_chunk_index += 1 |
|
else: |
|
current_chunk_index = 0 |
|
|
|
last_page_id = current_page_id |
|
chunk_id = f"{current_page_id}:{current_chunk_index}" |
|
chunk.metadata["id"] = chunk_id |
|
|
|
return chunks |
|
|
|
@app.route("/pdf", methods=["POST"]) |
|
def receive_pdf(): |
|
media_url = request.values.get("MediaUrl", None) |
|
if media_url: |
|
save_pdf_and_update_database(media_url) |
|
return "PDF processed and saved successfully." |
|
return "No media URL found." |
|
|
|
@app.route("/whatsapp", methods=["POST"]) |
|
def incoming_whatsapp(): |
|
media_url = request.values.get("MediaUrl", None) |
|
from_number = request.values.get("From", "").strip() |
|
from_number = from_number[2:] if from_number.startswith("91") else from_number |
|
incoming_msg = request.values.get('Body', '').lower() |
|
response = MessagingResponse() |
|
message = response.message() |
|
|
|
if media_url: |
|
extension = os.path.splitext(media_url)[1] |
|
if extension.lower() == ".pdf": |
|
media_filepath = download_and_save_as_txt(media_url, account_sid, auth_token) |
|
save_pdf_and_update_database(media_url) |
|
message.body("The PDF was processed successfully.") |
|
else: |
|
message.body("Please send a PDF file.") |
|
return str(response) |
|
|
|
if 'get weather for' in incoming_msg: |
|
city = incoming_msg.replace("get weather for", "") |
|
temperature = get_weather(city) |
|
message.body(f'The temperature in {city} is {temperature}.') |
|
return str(response) |
|
|
|
if 'get rates' in incoming_msg: |
|
message.body(get_rates()) |
|
return str(response) |
|
|
|
if 'get news' in incoming_msg: |
|
message.body(get_news()) |
|
return str(response) |
|
|
|
if 'pest' in incoming_msg: |
|
text = predict_pest(media_filepath) |
|
message.body(text) |
|
return str(response) |
|
|
|
if 'disease' in incoming_msg: |
|
text = predict_disease(media_filepath) |
|
message.body(text) |
|
return str(response) |
|
|
|
if 'question:' in incoming_msg: |
|
conversation_memory.add_to_memory(f"User: {incoming_msg}") |
|
chat_history = "\n".join(conversation_memory.get_memory()) |
|
response_text = generate_response(incoming_msg.replace("question:", ""), chat_history) |
|
conversation_memory.add_to_memory(f"Assistant: {response_text}") |
|
message.body(response_text) |
|
return str(response) |
|
|
|
if 'query:' in incoming_msg: |
|
query = incoming_msg.replace("query:", "").strip() |
|
response_text = query_rag(query) |
|
message.body(response_text) |
|
return str(response) |
|
|
|
message.body("I'm sorry, I don't understand that command.") |
|
return str(response) |
|
|
|
if __name__ == "__main__": |
|
app.run(debug=True) |
|
|