Add

app.py

@@ -130,6 +130,10 @@ class LLMProvider:
                 return self._generate_openai(prompt, model, temperature, max_tokens)
             elif self.provider == "huggingface":
                 return self._generate_huggingface(prompt, model, temperature, max_tokens)
+            elif self.provider == "deepseek":
+                return self._generate_deepseek(prompt, model, temperature, max_tokens)
+            elif self.provider == "hf_local":
+                return self._generate_hf_local(prompt, model, temperature, max_tokens)
             else:
                 raise ValueError(f"ไม่รองรับ provider: {self.provider}")
         except Exception as e:
@@ -164,6 +168,52 @@ class LLMProvider:
         )
         return response.choices[0].message.content
     
+    def _generate_deepseek(self, prompt, model, temperature, max_tokens):
+        url = "https://api.deepseek.com/v1/chat/completions"
+        headers = {
+            "Authorization": f"Bearer {self.api_key}",
+            "Content-Type": "application/json"
+        }
+        payload = {
+            "model": model,
+            "messages": [
+                {"role": "user", "content": prompt}
+            ],
+            "temperature": temperature,
+            "max_tokens": max_tokens
+        }
+        response = requests.post(url, headers=headers, json=payload)
+        response.raise_for_status()
+        result = response.json()
+        # DeepSeek API returns: {"choices":[{"message":{"role":"assistant","content":"..."}}], ...}
+        return result["choices"][0]["message"]["content"]
+
+    def _generate_hf_local(self, prompt, model, temperature, max_tokens):
+        # โหลดโมเดลและ tokenizer แค่ครั้งแรก (cache ใน instance)
+        if not hasattr(self, "_hf_local_model") or self._hf_local_model_name != model:
+            from transformers import AutoModelForCausalLM, AutoTokenizer
+            import torch
+            self._hf_local_model_name = model
+            self._hf_local_tokenizer = AutoTokenizer.from_pretrained(model)
+            self._hf_local_model = AutoModelForCausalLM.from_pretrained(model)
+            self._hf_local_model.eval()
+        tokenizer = self._hf_local_tokenizer
+        model = self._hf_local_model
+        import torch
+        inputs = tokenizer(prompt, return_tensors="pt")
+        with torch.no_grad():
+            outputs = model.generate(
+                **inputs,
+                max_new_tokens=max_tokens,
+                temperature=temperature,
+                do_sample=True
+            )
+        result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        # ตัด prompt ออกถ้ามี
+        if result.startswith(prompt):
+            result = result[len(prompt):].strip()
+        return result
+
     def _generate_huggingface(self, prompt, model, temperature, max_tokens):
         headers = {"Authorization": f"Bearer {self.api_key}"}
         response = requests.post(
@@ -546,7 +596,11 @@ def main_workflow(source_type, path_or_name, llm_provider_type, api_key, base_ur
         # 3. Generate new samples
         if n_generate > 0:
             progress_text += f"✨ กำลัง generate {n_generate} samples ใหม่ ({generation_type})...\n"
-            new_samples = generate_new_samples(samples, llm_provider, generation_type, n_generate, custom_prompt)
+            if llm_provider_type == "huggingface":
+                with gr.Progress(track_tqdm=True, desc="กำลัง generate ด้วย Hugging Face..."):
+                    new_samples = generate_new_samples(samples, llm_provider, generation_type, n_generate, custom_prompt)
+            else:
+                new_samples = generate_new_samples(samples, llm_provider, generation_type, n_generate, custom_prompt)
             samples.extend(new_samples)
             progress_text += f"✅ Generate สำเร็จ {len(new_samples)} samples ใหม่\n"
         
@@ -565,14 +619,22 @@ def main_workflow(source_type, path_or_name, llm_provider_type, api_key, base_ur
         # 5. Translation
         if target_language and target_language != "none":
             progress_text += f"🌐 กำลังแปลเป็น {target_language}...\n"
-            translated = translate_to_multilingual(samples, llm_provider, target_language)
+            if llm_provider_type == "huggingface":
+                with gr.Progress(track_tqdm=True, desc="กำลังแปลด้วย Hugging Face..."):
+                    translated = translate_to_multilingual(samples, llm_provider, target_language)
+            else:
+                translated = translate_to_multilingual(samples, llm_provider, target_language)
             samples.extend(translated)
             progress_text += f"✅ แปลภาษาสำเร็จ {len(translated)} samples\n"
         
         # 6. Add multiple choice
         if add_multiple_choice:
             progress_text += "📝 กำลังเพิ่ม multiple choice options...\n"
-            samples = add_multiple_choice_options(samples, llm_provider)
+            if llm_provider_type == "huggingface":
+                with gr.Progress(track_tqdm=True, desc="กำลังเพิ่มตัวเลือกด้วย Hugging Face..."):
+                    samples = add_multiple_choice_options(samples, llm_provider)
+            else:
+                samples = add_multiple_choice_options(samples, llm_provider)
             progress_text += "✅ เพิ่ม multiple choice เสร็จสิ้น\n"
         
         # 7. Export