Upload 9 files

backend/api.py

@@ -0,0 +1,74 @@
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+import pandas as pd
+from pathlib import Path
+
+# === 1. Setup API dan CORS ===
+app = FastAPI()
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# === 2. Global Setup (Model, Tokenizer, Data) ===
+BASE_DIR = Path(__file__).resolve().parent
+MODEL_DIR = BASE_DIR / "bert_chatbot_model"   # folder, bukan .onnx
+DATASET_PATH = BASE_DIR / "dataset_chatbot_template.xlsx"
+
+try:
+    tokenizer = AutoTokenizer.from_pretrained(str(MODEL_DIR))
+    model = AutoModelForSequenceClassification.from_pretrained(str(MODEL_DIR))
+    df_jawaban = pd.read_excel(DATASET_PATH)
+
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    model.to(device)
+    model.eval()
+except Exception as e:
+    print(f"❌ FATAL ERROR: {e}")
+
+responses = {
+    "about_me": "I am a passionate developer specializing in AI and web development.",
+    "skills": "My main skills are HTML5, CSS3, JavaScript, Laravel, Node.js, Database, TensorFlow, PyTorch, Firebase, and Jupyter Notebook.",
+    "projects": "Some of my projects are Mobile Apps Bald Detection and Jupyter Notebook Bald Detection.",
+    "experience": "I have worked as IT Support, AI Engineer, and Freelancer on multiple projects.",
+    "career_goal": "My career goal is to become a Full Stack Developer and Machine Learning Engineer.",
+    "greeting": "Hello! How can I help you regarding this portfolio?",
+    "fallback": "I'm sorry, I don't understand. Please ask another question."
+}
+
+class ChatRequest(BaseModel):
+    text: str
+
+@app.get("/")
+async def root():
+    return {"message": "🚀 Chatbot API running on Hugging Face"}
+
+@app.post("/chatbot")
+async def chat(req: ChatRequest):
+    if 'model' not in globals():
+        return {"response": responses["fallback"], "intent": "error_loading"}
+
+    try:
+        inputs = tokenizer(req.text, return_tensors="pt", padding=True, truncation=True, max_length=128).to(device)
+        with torch.no_grad():
+            outputs = model(**inputs)
+            pred_id = torch.argmax(outputs.logits, dim=1).item()
+
+        intent = model.config.id2label.get(pred_id, "fallback")
+
+        try:
+            jawaban = df_jawaban.loc[df_jawaban['Intent'] == intent, 'Jawaban_ID'].iloc[0]
+        except IndexError:
+            jawaban = responses.get(intent, responses["fallback"])
+
+        return {"intent": intent, "response": jawaban}
+
+    except Exception as e:
+        print(f"❌ Runtime Error: {e}")
+        return {"response": "Internal server error"}

backend/models/bert-base-multilingual-cased/config.json

@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "about_me",
+    "1": "career_goal",
+    "2": "experience",
+    "3": "fallback",
+    "4": "greeting",
+    "5": "projects",
+    "6": "skills"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "about_me": 0,
+    "career_goal": 1,
+    "experience": 2,
+    "fallback": 3,
+    "greeting": 4,
+    "projects": 5,
+    "skills": 6
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.56.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

backend/models/bert-base-multilingual-cased/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

backend/models/bert-base-multilingual-cased/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}