PyPI - ws-bom-robot-app - Versions diffs - 0.0.58__tar.gz → 0.0.59__tar.gz - Mend

@@ -4,7 +4,7 @@ from ws_bom_robot_app.llm.models.api import LlmAppTool
 from ws_bom_robot_app.llm.providers.llm_manager import LlmInterface
 from ws_bom_robot_app.llm.vector_store.db.manager import VectorDbManager
 from ws_bom_robot_app.llm.tools.utils import getRandomWaitingMessage, translate_text
-from ws_bom_robot_app.llm.tools.models.main import NoopInput,DocumentRetrieverInput,ImageGeneratorInput,LlmChainInput
+from ws_bom_robot_app.llm.tools.models.main import NoopInput,DocumentRetrieverInput,ImageGeneratorInput,LlmChainInput,SearchOnlineInput
 from pydantic import BaseModel, ConfigDict
 class ToolConfig(BaseModel):
@@ -143,6 +143,35 @@ class ToolManager:
           return result
+    async def search_online(self, query: str):
+        from ws_bom_robot_app.llm.tools.utils import fetch_page, extract_content_with_trafilatura
+        from langchain_community.utilities import DuckDuckGoSearchAPIWrapper
+        import aiohttp, asyncio, ast
+        # Wrapper DuckDuckGo
+        search = DuckDuckGoSearchAPIWrapper(max_results=10)
+        try:
+          raw_results = search.results(query, max_results=10)
+        except Exception as e:
+            print(f"[!] Errore ricerca: {e}")
+        urls = [r["link"] for r in raw_results]
+        async with aiohttp.ClientSession() as session:
+            tasks = [fetch_page(session, url) for url in urls]
+            responses = await asyncio.gather(*tasks)
+        final_results = []
+        for item in responses:
+            url = item["url"]
+            html = item["html"]
+            if html:
+                content = await extract_content_with_trafilatura(html)
+                if content:
+                    final_results.append({"url": url, "content": content})
+                else:
+                    final_results.append({"url": url, "content": "No content found"})
+            else:
+                final_results.append({"url": url, "content": "Page not found"})
+        return final_results
     #endregion
     #class variables (static)
@@ -150,6 +179,7 @@ class ToolManager:
         "document_retriever": ToolConfig(function=document_retriever, model=DocumentRetrieverInput),
         "image_generator": ToolConfig(function=image_generator, model=ImageGeneratorInput),
         "llm_chain": ToolConfig(function=llm_chain, model=LlmChainInput),
+        "search_online": ToolConfig(function=search_online, model=SearchOnlineInput),
     }
     #instance methods

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ws_bom_robot_app
-Version: 0.0.58
+Version: 0.0.59
 Summary: A FastAPI application serving ws bom/robot/llm platform ai.
 Home-page: https://github.com/websolutespa/bom
 Author: Websolute Spa
@@ -17,6 +17,7 @@ Requires-Dist: pydantic==2.10.6
 Requires-Dist: pydantic-settings==2.7.1
 Requires-Dist: fastapi[standard]==0.115.8
 Requires-Dist: chevron==0.14.0
+Requires-Dist: trafilatura==2.0.0
 Requires-Dist: langchain==0.3.25
 Requires-Dist: langchain-community==0.3.24
 Requires-Dist: langchain-core==0.3.59
@@ -48,6 +49,7 @@ Requires-Dist: unstructured-ingest[sharepoint]
 Requires-Dist: unstructured-ingest[slack]
 Requires-Dist: html5lib==1.1
 Requires-Dist: markdownify==0.14.1
+Requires-Dist: duckduckgo-search==8.0.4
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier

@@ -6,6 +6,7 @@ pydantic==2.10.6
 pydantic-settings==2.7.1
 fastapi[standard]==0.115.8
 chevron==0.14.0
+trafilatura==2.0.0
 #framework
 langchain==0.3.25
@@ -46,3 +47,4 @@ html5lib==1.1 #beautifulsoup4 parser
 #integrations
 markdownify==0.14.1 #sitemap
+duckduckgo-search==8.0.4

@@ -4,7 +4,7 @@ _requirements = [line.split('#')[0].strip() for line in open("requirements.txt")
 setup(
     name="ws_bom_robot_app",
-    version="0.0.58",
+    version="0.0.59",
     description="A FastAPI application serving ws bom/robot/llm platform ai.",
     long_description=open("README.md", encoding='utf-8').read(),
     long_description_content_type="text/markdown",

@@ -9,3 +9,5 @@ class ImageGeneratorInput(BaseModel):
   language: str = Field(description="Language of the query. Default is 'it'", default="it")
 class LlmChainInput(BaseModel):
   input: str = Field(description="Input to the LLM chain")
+class SearchOnlineInput(BaseModel):
+  query: str = Field(description="The search query string")

@@ -23,3 +23,19 @@ async def translate_text(llm: LlmInterface, language, text: str, callbacks: list
   prompt = PromptTemplate.from_template(sys_message)
   chain = prompt | llm.get_llm()
   await chain.ainvoke({"language":language, "testo_da_tradurre": text}, {"callbacks": callbacks})
+async def fetch_page(session, url):
+    try:
+        async with session.get(url, timeout=10, ssl=False) as response:
+            if response.status == 200:
+                text = await response.text()
+                return {"url": url, "html": text}
+            else:
+                return {"url": url, "html": None}
+    except Exception as e:
+        return {"url": url, "html": None}
+async def extract_content_with_trafilatura(html):
+    """Estrae solo il testo principale usando trafilatura"""
+    import trafilatura
+    return trafilatura.extract(html)

ws-bom-robot-app 0.0.58__tar.gz → 0.0.59__tar.gz

ws-bom-robot-app 0.0.58tar.gz → 0.0.59tar.gz