Update app.py

app.py

@@ -113,12 +113,112 @@ Answer:"""
             return f"Error executing code:\n{traceback.format_exc()}"
 
 
-from transformers.tools import (
-    DocumentQuestionAnsweringTool,
-    ImageQuestionAnsweringTool,
-    TranslationTool,
-    PythonInterpreterTool
-)
+from transformers import pipeline
+from smolagents import Tool
+
+class TranslationTool(Tool):
+    name = "translate_text"
+    description = "Translate text from one language to another."
+
+    inputs = {
+        "text": {"type": "string", "description": "Text to translate"},
+        "src_lang": {"type": "string", "description": "Source language code"},
+        "tgt_lang": {"type": "string", "description": "Target language code"},
+    }
+    output_type = "string"
+
+    def __init__(self):
+        self.translator = pipeline("translation", model="Helsinki-NLP/opus-mt-en-fr")
+
+    def forward(self, text: str, src_lang: str, tgt_lang: str) -> str:
+        return self.translator(text)[0]["translation_text"]
+
+
+
+from transformers import pipeline
+from smolagents import Tool
+from PIL import Image
+
+class HuggingFaceDocumentQATool(Tool):
+    name = "document_qa"
+    description = "Answer questions from document images (e.g., scanned invoices)."
+    inputs = {
+        "image_path": {"type": "string", "description": "Path to the image file"},
+        "question": {"type": "string", "description": "Question to ask about the document"}
+    }
+    output_type = "string"
+
+    def __init__(self):
+        self.pipeline = pipeline("document-question-answering", model="impira/layoutlm-document-qa")
+
+    def forward(self, image_path: str, question: str) -> str:
+        image = Image.open(image_path)
+        result = self.pipeline(image, question=question)
+        return result[0]['answer']
+
+
+from transformers import BlipProcessor, BlipForQuestionAnswering
+
+class HuggingFaceImageQATool(Tool):
+    name = "image_qa"
+    description = "Answer questions about an image."
+    inputs = {
+        "image_path": {"type": "string", "description": "Path to image"},
+        "question": {"type": "string", "description": "Question about the image"}
+    }
+    output_type = "string"
+
+    def __init__(self):
+        self.processor = BlipProcessor.from_pretrained("Salesforce/blip-vqa-base")
+        self.model = BlipForQuestionAnswering.from_pretrained("Salesforce/blip-vqa-base")
+
+    def forward(self, image_path: str, question: str) -> str:
+        image = Image.open(image_path)
+        inputs = self.processor(image, question, return_tensors="pt")
+        out = self.model.generate(**inputs)
+        return self.processor.decode(out[0], skip_special_tokens=True)
+
+
+
+from transformers import pipeline
+
+class HuggingFaceTranslationTool(Tool):
+    name = "translate"
+    description = "Translate text from English to another language."
+    inputs = {
+        "text": {"type": "string", "description": "Text to translate"}
+    }
+    output_type = "string"
+
+    def __init__(self):
+        self.translator = pipeline("translation", model="Helsinki-NLP/opus-mt-en-fr")
+
+    def forward(self, text: str) -> str:
+        return self.translator(text)[0]["translation_text"]
+
+
+
+import io
+import contextlib
+
+class PythonCodeExecutionTool(Tool):
+    name = "run_python"
+    description = "Execute Python code and return result."
+    inputs = {
+        "code": {"type": "string", "description": "Python code to execute"}
+    }
+    output_type = "string"
+
+    def forward(self, code: str) -> str:
+        output = io.StringIO()
+        try:
+            with contextlib.redirect_stdout(output):
+                exec(code, {})
+            return output.getvalue().strip()
+        except Exception as e:
+            return f"Error: {str(e)}"
+
+
 
 
 #from smolagents import Tool
@@ -297,10 +397,10 @@ class BasicAgent:
         arxiv_search_tool = ArxivSearchTool()
 
         # ✅ Add Hugging Face default tools
-        doc_qa_tool = DocumentQuestionAnsweringTool()
-        image_qa_tool = ImageQuestionAnsweringTool()
-        translation_tool = TranslationTool()
-        python_tool = PythonInterpreterTool()
+        doc_qa_tool = HuggingFaceDocumentQATool()
+        image_qa_tool = HuggingFaceImageQATool()
+        translation_tool = HuggingFaceTranslationTool()
+        python_tool = PythonCodeExecutionTool()
 
         system_prompt = """You are my general AI assistant...
 Always return your final result in the format: