Base

app.py

@@ -0,0 +1,69 @@
+import os
+import gradio as gr
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+# ----------------------------
+# Intent mapping (inlined)
+# ----------------------------
+ID_TO_INTENT = {
+    0: "price_check",
+    1: "product_information",
+    2: "product_search",
+    3: "promo_discount",
+    4: "return_refund",
+    5: "stock_check",
+}
+
+INTENT_TO_ID = {intent: idx for idx, intent in ID_TO_INTENT.items()}
+
+def get_intent_from_id(label_id: int) -> str:
+    return ID_TO_INTENT.get(label_id, f"unknown_intent_{label_id}")
+
+# ----------------------------
+# Model load
+# ----------------------------
+BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+MODEL_DIR = os.path.join(BASE_DIR, "models", "intent_bert_model")  # adjust if your folder name differs
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+tok = AutoTokenizer.from_pretrained(MODEL_DIR)
+mdl = AutoModelForSequenceClassification.from_pretrained(MODEL_DIR).to(device)
+mdl.eval()
+
+# ----------------------------
+# API function
+# ----------------------------
+def intent_only(message: str):
+    message = (message or "").strip()
+    if not message:
+        return {"intent": None, "confidence": 0.0}
+
+    inputs = tok(message, return_tensors="pt", truncation=True, max_length=256).to(device)
+
+    with torch.no_grad():
+        logits = mdl(**inputs).logits[0]
+        probs = torch.softmax(logits, dim=-1)
+
+    label_id = int(torch.argmax(probs).item())
+    confidence = float(torch.max(probs).item())
+
+    return {
+        "intent": get_intent_from_id(label_id),
+        "confidence": confidence,
+        "label_id": label_id,  # remove later if you want
+    }
+
+# ----------------------------
+# Gradio app (minimal UI, API-first)
+# ----------------------------
+demo = gr.Interface(
+    fn=intent_only,
+    inputs=gr.Textbox(label="message"),
+    outputs=gr.JSON(label="intent"),
+    title="Pure Intent Classifier (No GenAI)",
+)
+
+demo.api_name = "/intent"
+demo.launch()

models/intent_bert_model/config.json

@@ -0,0 +1,42 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

models/intent_bert_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74f4cb1c8682cb84b405be4cd461ea889c88c2e1796a7e129030f2d4eab14b16
+size 437970952

models/intent_bert_model/special_tokens_map.json

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

models/intent_bert_model/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}