Deployment file added

.gitattributes

@@ -6,6 +6,7 @@
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
+*.t7 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.mlmodel filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,30 @@
+FROM python:3.9  
+
+RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y  # Install Rust early
+
+COPY requirements.txt requirements.txt
+RUN pip install --upgrade pip
+RUN pip install --no-cache-dir -r requirements.txt
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    bzip2 \
+    g++ \
+    git \
+    graphviz \
+    libgl1-mesa-glx \
+    libhdf5-dev \
+    openmpi-bin \
+    wget \
+    python3-tk && \
+    rm -rf /var/lib/apt/lists/*
+
+RUN useradd -m -u 1000 myuser
+USER myuser
+
+COPY --chown=myuser app app
+
+# COPY . .
+
+EXPOSE 8001
+
+CMD ["python", "app/main.py"]

README.md

@@ -1,11 +1,12 @@
 ---
-title: Gpt2 Email Generation
-emoji: 🏆
-colorFrom: blue
-colorTo: yellow
+title: Ai Chatbot Email Subject Generator
+emoji: 👁
+colorFrom: green
+colorTo: purple
 sdk: docker
 pinned: false
 license: mit
+app_port: 8001
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.0.1"

app/config.py

@@ -0,0 +1,25 @@
+import sys
+from typing import List
+
+from pydantic import AnyHttpUrl, BaseSettings
+
+class Settings(BaseSettings):
+    API_V1_STR: str = "/api/v1"
+
+    # Meta
+ 
+    # BACKEND_CORS_ORIGINS is a comma-separated list of origins
+    # e.g: http://localhost,http://localhost:4200,http://localhost:3000
+    BACKEND_CORS_ORIGINS: List[AnyHttpUrl] = [
+        "http://localhost:3000",  # type: ignore
+        "http://localhost:8000",  # type: ignore
+        "https://localhost:3000",  # type: ignore
+        "https://localhost:8000",  # type: ignore
+    ]
+
+    PROJECT_NAME: str = "Recognition API"
+
+    class Config:
+        case_sensitive = True
+
+settings = Settings()

app/main.py

@@ -0,0 +1,93 @@
+import sys
+from pathlib import Path
+import os
+sys.path.append(str(Path(__file__).resolve().parent.parent))
+#print(sys.path)
+from typing import Any
+from fastapi import FastAPI, Request, APIRouter, Form
+from fastapi.staticfiles import StaticFiles
+from fastapi.templating import Jinja2Templates
+from fastapi.middleware.cors import CORSMiddleware
+from app.config import settings
+from app import __version__
+from app.pyfiles import subject_gen
+import numpy as np
+import pandas as pd
+# from transformers import  GPT2Tokenizer ,GPT2Model
+
+current_path = os.path.dirname(os.path.abspath(__file__))
+
+# model = GPT2Model.from_pretrained("gpt2")
+# tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
+
+# checkpoint1 = os.path.join(current_path, "pyfiles") 
+# checkpoint = os.path.join(checkpoint1, "gpt_tokenizer") 
+# model.save_pretrained(checkpoint)
+# tokenizer.save_pretrained(checkpoint) 
+
+app = FastAPI(
+    title=settings.PROJECT_NAME, openapi_url=f"{settings.API_V1_STR}/openapi.json"
+)
+# app.mount("/static", StaticFiles(directory="app/static"), name="static")
+
+
+# To access Templates directory
+templates = Jinja2Templates(directory="app/templates")
+
+email_inp = None
+####################################  Home Page endpoints  #################################################
+@app.get("/")
+async def root(request: Request):
+    return templates.TemplateResponse("index.html", {'request': request,})
+
+
+
+@app.get("/email_input/")
+async def email_input_root(request: Request):
+    print("hi im in email input" )
+    return templates.TemplateResponse("email_input.html", {'request': request,})
+
+
+
+@app.post("/subject_generation/")
+async def create_upload_files(request: Request , paragraphInput: str = Form(...)):
+    global email_inp
+    print("hi im in subject gen", paragraphInput )
+    print("########################",request)
+    input_email = paragraphInput
+    print('********************',input_email)
+    if 'text' in input_email.content_type:
+        contents = await input_email.read()
+
+        email_inp = 'app/static/' + input_email.filename
+
+        # Save the contents to the text file
+        with open(email_inp, 'w', encoding='utf-8') as f:
+            f.write(contents.decode('utf-8'))
+    print('********************',email_inp)
+    email = ""
+    with open(email_inp, 'r', encoding='utf-8') as f:
+        email =f.read()
+    result = subject_gen.subject_gen_func(email)
+    print(result)
+    
+    return templates.TemplateResponse("subject_generation.html", {"request": request,
+                                                       "result":result,
+                                                       "email":email,})
+
+
+# Set all CORS enabled origins
+if settings.BACKEND_CORS_ORIGINS:
+    app.add_middleware(
+        CORSMiddleware,
+        allow_origins=[str(origin) for origin in settings.BACKEND_CORS_ORIGINS],
+        allow_credentials=True,
+        allow_methods=["*"],
+        allow_headers=["*"],
+    )
+
+
+# Start app
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8001)

app/pyfiles/gpt2_3epoch/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0",
+  "use_cache": true,
+  "vocab_size": 50260
+}

app/pyfiles/gpt2_3epoch/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.36.0"
+}

app/pyfiles/gpt2_3epoch/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05bd44466157c4b1e49430a2041682efd02563c1ad3db75aaf655b63cf35c9e
+size 497783424

app/pyfiles/gpt2_3epoch/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32212753abe04ec447858f468942187b9608277b6254812afb5c6abb3a119fd6
+size 995660293

app/pyfiles/gpt2_3epoch/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d42ae0a45828f61b6a23c6010b52b2e9e8c0c4f0e8e5804c63f017ff1c8bd68
+size 14575

app/pyfiles/gpt2_3epoch/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed6905d5273c406da5dfd33b20f749017129ee92a89b048639acfac93faeb025
+size 627

app/pyfiles/gpt2_3epoch/trainer_state.json

@@ -0,0 +1,141 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.3250207813798838,
+  "eval_steps": 1000,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.65839800443459e-05,
+      "loss": 5.6144,
+      "step": 500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.311945676274945e-05,
+      "loss": 3.3585,
+      "step": 1000
+    },
+    {
+      "epoch": 0.55,
+      "eval_loss": 3.1234283447265625,
+      "eval_runtime": 415.1946,
+      "eval_samples_per_second": 34.769,
+      "eval_steps_per_second": 4.347,
+      "step": 1000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.9654933481152996e-05,
+      "loss": 3.2619,
+      "step": 1500
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 3.619041019955654e-05,
+      "loss": 3.1664,
+      "step": 2000
+    },
+    {
+      "epoch": 1.11,
+      "eval_loss": 2.9533257484436035,
+      "eval_runtime": 414.0939,
+      "eval_samples_per_second": 34.862,
+      "eval_steps_per_second": 4.359,
+      "step": 2000
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 3.272588691796009e-05,
+      "loss": 3.0865,
+      "step": 2500
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 2.9261363636363635e-05,
+      "loss": 3.0651,
+      "step": 3000
+    },
+    {
+      "epoch": 1.66,
+      "eval_loss": 2.849994659423828,
+      "eval_runtime": 413.8155,
+      "eval_samples_per_second": 34.885,
+      "eval_steps_per_second": 4.362,
+      "step": 3000
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 2.5796840354767186e-05,
+      "loss": 3.0161,
+      "step": 3500
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 2.2332317073170734e-05,
+      "loss": 2.9496,
+      "step": 4000
+    },
+    {
+      "epoch": 2.22,
+      "eval_loss": 2.7711386680603027,
+      "eval_runtime": 414.5048,
+      "eval_samples_per_second": 34.827,
+      "eval_steps_per_second": 4.355,
+      "step": 4000
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.886779379157428e-05,
+      "loss": 2.9008,
+      "step": 4500
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 1.5403270509977826e-05,
+      "loss": 2.9216,
+      "step": 5000
+    },
+    {
+      "epoch": 2.77,
+      "eval_loss": 2.719022750854492,
+      "eval_runtime": 413.676,
+      "eval_samples_per_second": 34.897,
+      "eval_steps_per_second": 4.363,
+      "step": 5000
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 1.1938747228381375e-05,
+      "loss": 2.8984,
+      "step": 5500
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 8.474223946784923e-06,
+      "loss": 2.8326,
+      "step": 6000
+    },
+    {
+      "epoch": 3.33,
+      "eval_loss": 2.6863553524017334,
+      "eval_runtime": 413.8185,
+      "eval_samples_per_second": 34.885,
+      "eval_steps_per_second": 4.362,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7216,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 8000641580544000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

app/pyfiles/gpt2_3epoch/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a328fb2002f110a8fb6b6bc9adb7284bf489e232bcc66216e1d9cf07892857eb
+size 4283

app/pyfiles/gpt_tokenizer/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<email>": 50257,
+  "<subject>": 50258,
+  "[PAD]": 50259
+}

app/pyfiles/gpt_tokenizer/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

app/pyfiles/gpt_tokenizer/tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<email>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "<subject>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

app/pyfiles/subject_gen.py

@@ -0,0 +1,28 @@
+import os
+from pathlib import Path
+import numpy as np
+import torch
+from transformers import GPT2LMHeadModel, GPT2Tokenizer ,GPT2Model
+
+current_path = os.path.dirname(os.path.abspath(__file__))
+tokenizer_path = os.path.join(current_path, "gpt_tokenizer")
+model_path = os.path.join(current_path, "gpt2_3epoch")
+tokenizer = GPT2Tokenizer.from_pretrained(tokenizer_path) # also try gpt2-medium
+model = GPT2LMHeadModel.from_pretrained(model_path)
+extra_tokens = ["<email>", "<subject>"]
+tokenizer.add_tokens(extra_tokens)
+tokenizer.add_special_tokens({'pad_token': '[PAD]'})
+model.resize_token_embeddings(len(tokenizer))
+
+def subject_gen_func(email):
+    device = "cpu"
+    prompt = email
+    input_ids = tokenizer.encode(prompt, return_tensors="pt").to(device)
+    attention_mask = torch.ones_like(input_ids)
+    pad_token_id = tokenizer.eos_token_id
+    output_ids = model.generate(input_ids, max_length=1024, num_return_sequences=1,attention_mask=attention_mask,
+            pad_token_id=pad_token_id)
+
+
+    generated_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+    return generated_text.split("<subject>")[1].replace("<eos>","")

app/templates/email_input.html

@@ -0,0 +1,32 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <title>Index</title>
+</head>
+<body>
+    <div>
+        <h1 style="background-color:LightGray;">
+            <center>Email Subject Line Generator </center>
+        </h1>
+    </div>
+    <div>
+        <fieldset>
+        <ul>
+            <!li>
+            <br>
+            <form action="/subject_generation/" enctype="multipart/form-data" method="post">
+                <span style="font-weight:bold;font-family:sans-serif">Enter Email:</span> <br><br>
+				<textarea name="paragraphInput" rows="5" cols="100"></textarea>
+                <br><br><br><br>
+                <button type="submit">Generate Subject</button>
+            </form>
+            <!/li>
+            <br><br>
+            <form action="/" method="get">
+                <button type="submit">Home</button>
+            </form>
+        </ul>
+        </fieldset>
+    </div>
+</body>
+</html>

app/templates/index.html

@@ -0,0 +1,43 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <title>Index</title>
+    <style>
+        /* Add a style block for custom CSS */
+        .button-container {
+            text-align: center; /* Center the buttons */
+        }
+
+        .button-container form {
+            display: inline-block; /* Display forms (buttons) in a line */
+            margin: 0 10px; /* Add margin between buttons for spacing */
+        }
+    </style>
+</head>
+<body>
+    <div>
+        <h1 style="background-color:LightGray;">
+            <center>AI Chat Bot</center>
+        </h1>
+    </div>
+    <div>
+        <fieldset>
+            <ul>
+                <div>
+                    <h2 style="background-color:white;">
+                        <center>Select Task</center>
+                    </h2>
+                </div>
+                <br><br><br>
+                <div class="button-container"> <!-- Wrap buttons in a container -->
+                    
+                        <form action="{{ url_for('email_input_root') }}"><button>Email Subject Generator</button></form>
+                        <form ><button>AI ML Question Answering Chatbot</button></form>
+                    
+                </div>
+                <br>
+            </ul>
+        </fieldset>
+    </div>
+</body>
+</html>

app/templates/subject_generation.html

@@ -0,0 +1,39 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <title>Predict</title>
+</head>
+<body>
+    <div>
+        <h1 style="background-color:LightGray;">
+            <center>Subject Generation </center>
+        </h1>
+    </div>
+    <div>
+        <fieldset>
+
+            <h3><center><span style="font-weight:bold;font-family:sans-serif">Email:</span></Input></center></h3> 
+            <p>
+                <center>
+                    <span style="font-weight:bold;color:blue"> {{email}}</span>
+                </center>
+            </p>
+            <br><br>
+            <h3>
+                <center>
+                    <span style="font-weight:bold;font-family:sans-serif">Subject:</span> 
+                    <span style="font-weight:bold;color:blue"> {{result}}</span>
+                </center>
+            </h3>
+            <br><br>
+            <form action="/email_input/" method="get">
+                <center><button type="submit">Check Another Input</button></center>
+            </form>
+            <br>
+            <form action="/" method="get">
+                <center><button type="submit">Home</button></center>
+            </form>
+        </fieldset>
+    </div>
+</body>
+</html>

requirements.txt

@@ -0,0 +1,14 @@
+uvicorn==0.17.6
+fastapi==0.99.1
+pydantic==1.10.10
+requests==2.23.0
+jinja2==3.1.2
+python-multipart
+numpy
+pandas
+setuptools-rust
+transformers
+accelerate
+transformers[torch]
+
+