from fastapi import FastAPI,Request,File,UploadFile from fastapi.templating import Jinja2Templates from fastapi.staticfiles import StaticFiles from fastapi.responses import HTMLResponse,JSONResponse from fastapi.middleware.cors import CORSMiddleware import pandas as pd import re import io import base64 import matplotlib.pyplot as plt import torch from transformers import pipeline,VisionEncoderDecoderModel,ViTImageProcessor,AutoTokenizer from transformers import BartForConditionalGeneration, BartTokenizer from transformers import AutoModelForCausalLM, AutoTokenizer import fitz from docx import Document from pptx import Presentation import seaborn as sns import PIL.Image as Image import fitz import os os.environ["MPLCONFIGDIR"] = "/tmp/matplotlib" os.environ["XDG_CACHE_HOME"] = "/tmp/cache" os.environ["TRANSFORMERS_CACHE"] = "/tmp/transformers" os.environ["HF_HOME"] = "/tmp/huggingface" app=FastAPI() app.add_middleware( CORSMiddleware, allow_origins=["*"], allow_credentials=True, allow_methods=["*"], allow_headers=["*"], ) try: #interpreter = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning") interpreter_model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning") interpreter_processor = ViTImageProcessor.from_pretrained("nlpconnect/vit-gpt2-image-captioning") interpreter_tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning") except Exception as exp: print("[ERROR] Can't load nlpconnect/vit-gpt2-image-captioning") print(str(exp)) #try: # summarizer = pipeline("summarization", model="facebook/bart-large-cnn",device=0) #except Exception as exp: # print("[ERROR] Can't load facebook/bart-large-cnn ") # print(str(exp)) try: summarizer_model = BartForConditionalGeneration.from_pretrained("facebook/bart-large-cnn") except OSError as e: print(f"[INFO] PyTorch weights not found. Falling back to TensorFlow weights.\n{e}") summarizer_model = BartForConditionalGeneration.from_pretrained("facebook/bart-large-cnn", from_tf=True) summarizer_tokenizer = BartTokenizer.from_pretrained("facebook/bart-large-cnn") #try: # generator = pipeline("text-generation", model="deepseek-ai/deepseek-coder-1.3b-instruct", device_map="auto") #except Exception as exp: # print("[ERROR] Can't load deepseek-ai/deepseek-coder-1.3b-instruct ") # print(str(exp)) try: generator_model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-1.3b-instruct", trust_remote_code=True) tokengenerator_modelizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-1.3b-instruct", trust_remote_code=True) except Exception as exp : print("[ERROR] Can't load deepseek-ai/deepseek-coder-1.3b-instruct ") print(str(exp)) app.mount("/static",StaticFiles(directory='static'),'static') templates = Jinja2Templates(directory='templates') @app.get("/",response_class=HTMLResponse) def index(req:Request): return templates.TemplateResponse('index.html',{'request':req}) @app.get("/summarization",response_class=HTMLResponse) def index(req:Request): return templates.TemplateResponse('Summarization.html',{'request':req}) @app.get("/datavisualisation",response_class=HTMLResponse) def index(req:Request): return templates.TemplateResponse('DataVisualisation.html',{'request':req}) @app.get("/imageinterpretation",response_class=HTMLResponse) def index(req:Request): return templates.TemplateResponse('ImageInterpretation.html',{'request':req}) @app.post("/caption") def caption(file:UploadFile=File(...)): extension = file.filename.split(".")[-1] Supported_extensions = ["png","jpg","jpeg"] if extension not in Supported_extensions: return {"error": "Unsupported file type"} image = Image.open(file.file) #caption = interpreter(image) pixel_values = interpreter_processor(images=image, return_tensors="pt").pixel_values output_ids = interpreter_model.generate(pixel_values, max_length=16, num_beams=4) caption = interpreter_tokenizer.decode(output_ids[0], skip_special_tokens=True) return {"caption":caption} #return {"caption": caption[0]['generated_text']} @app.post("/summerize") def summerzation(file:UploadFile=File(...)): extension = file.filename.split(".")[-1] if extension == "pdf": text = get_text_from_PDF(file.file) elif extension == "docx": text = get_text_from_DOC(file.file) elif extension == "pptx": text = get_text_from_PPT(file.file) elif extension == "xlsx": text = get_text_from_EXCEL(file.file) else: return {"error": "Unsupported file type"} if not text.strip(): return {"error": "File is empty"} result="" #for i in range(0,len(text),1024): # result+=summarizer(text, max_length=150, min_length=30, do_sample=False)[0]['summary_text'] return {"summary": result} @app.post("/plot") def plot(prompt:str,file:UploadFile=File(...)): try: extension = file.filename.split(".")[-1] Supported_extensions = ["xlsx","xls"] if extension not in Supported_extensions: return {"error": "Unsupported file type"} df = pd.read_excel(file.file) message = f""" You are a helpful assistant that helps users write Python code. ## Requirements: -you will be given a task and you will write the code to solve the task. -you have a dataset called **df** contains the following information: df.columns:{df.columns.to_list()} df.dtypes:{df.dtypes.to_dict()} -you have to write the code to solve the task using the dataset df. -you can use pandas to manipulate the dataframe. -you can use matplotlib to plot the data. -you can use seaborn to plot the data. -don't use print or input statements in the code. -don't use any other libraries except pandas, matplotlib, seaborn. -don't use any other functions except the ones provided in the libraries. -don't write the code for the dataframe creation. -exclude plt.show() from the code. -you have to write the code in a markdown code block. -make sure that the type of the chart is compatible with the dtypes of the columns -use only the column specified in the task. -you have to extract the column names and the plot type from the prompt bellow and use them in the code. -if the user task is not clear or there is an error like the column names are not in the dataframe, raise an error. ##Prompt: {prompt}. """ output = [{"generated_text":""}]#generator(message, max_length=1000) match = re.search(r'```python(.*?)```', output[0]["generated_text"], re.DOTALL) code ='' if not match: return {"error": "Can't generate the plot"} code = match.group(1).replace("plt.show()\n","") safe_globals={ "plt": plt, "sns": sns, "pd": pd, "df": df } try: exec(code,safe_globals) buf = io.BytesIO() plt.savefig(buf, format='png') buf.seek(0) base64_image = base64.b64encode(buf.getvalue()).decode('utf-8') return {"plot": f"data:image/png;base64,{base64_image}"} except Exception as e: return {"error": str(e)} except Exception as exp: return {"error":"Internel Server Error:"+str(exp)} def get_text_from_PDF(file): doc = fitz.open(file, filetype="pdf") text = "" for page in doc: text += page.get_text() return text def get_text_from_PPT(file): prs = Presentation(file) text = "" for slide in prs.slides: for shape in slide.shapes: if hasattr(shape, "text"): text += shape.text return text def get_text_from_DOC(file): doc = Document(file) text = "" for paragraph in doc.paragraphs: text += paragraph.text return text def get_text_from_EXCEL(file): df = pd.read_excel(file) text = df.to_string() return text