Update app.py

app.py

@@ -109,6 +109,130 @@ Answer:"""
 
 
 
+
+import requests
+from smolagents import Tool
+
+class ArxivSearchTool(Tool):
+    name = "arxiv_search"
+    description = "Search Arxiv for papers matching a query and return titles and links."
+    inputs = {
+        "query": {"type": "string", "description": "Search query for Arxiv papers"}
+    }
+    output_type = "string"
+
+    def forward(self, query: str) -> str:
+        url = "http://export.arxiv.org/api/query"
+        params = {
+            "search_query": query,
+            "start": 0,
+            "max_results": 3,
+            "sortBy": "relevance",
+            "sortOrder": "descending"
+        }
+        try:
+            response = requests.get(url, params=params, timeout=10)
+            response.raise_for_status()
+            # Simple parse titles and links (basic, for demo)
+            import xml.etree.ElementTree as ET
+            root = ET.fromstring(response.content)
+            ns = {"atom": "http://www.w3.org/2005/Atom"}
+
+            entries = root.findall("atom:entry", ns)
+            results = []
+            for entry in entries:
+                title = entry.find("atom:title", ns).text.strip().replace('\n', ' ')
+                link = entry.find("atom:id", ns).text.strip()
+                results.append(f"{title}\n{link}")
+            return "\n\n".join(results) if results else "No results found."
+        except Exception as e:
+            return f"Error during Arxiv search: {e}"
+
+
+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
 #from langchain_community.document_loaders import WikipediaLoader
 
@@ -283,6 +407,12 @@ class BasicAgent:
 
         # ✅ New Llama Tool
         code_llama_tool = CodeLlamaTool()
+        # ✅ Add Hugging Face default tools
+        arxiv_search_tool = ArxivSearchTool()
+        doc_qa_tool = HuggingFaceDocumentQATool()
+        image_qa_tool = HuggingFaceImageQATool()
+        translation_tool = HuggingFaceTranslationTool()
+        python_tool = PythonCodeExecutionTool()
 
         system_prompt = f"""
 You are my general AI assistant. Your task is to answer the question I asked.
@@ -301,6 +431,9 @@ If the answer is a comma-separated list, apply the above rules for each element
                 keywords_extract_tool, speech_to_text_tool,
                 visit_webpage_tool, final_answer_tool,
                 parse_excel_to_json, video_transcription_tool,
+                arxiv_search_tool,
+                doc_qa_tool, image_qa_tool,
+                translation_tool, python_tool, 
                 code_llama_tool  # 🔧 Add here
             ],
             add_base_tools=True