ws-bom-robot-app 0.0.60__tar.gz → 0.0.62__tar.gz

{ws_bom_robot_app-0.0.60/ws_bom_robot_app.egg-info → ws_bom_robot_app-0.0.62}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ws_bom_robot_app
-Version: 0.0.60
+Version: 0.0.62
 Summary: A FastAPI application serving ws bom/robot/llm platform ai.
 Home-page: https://github.com/websolutespa/bom
 Author: Websolute Spa
@@ -13,24 +13,23 @@ Description-Content-Type: text/markdown
 Requires-Dist: standardwebhooks==1.0.0
 Requires-Dist: apscheduler==3.11.0
 Requires-Dist: aiofiles==24.1.0
-Requires-Dist: pydantic==2.10.6
-Requires-Dist: pydantic-settings==2.7.1
-Requires-Dist: fastapi[standard]==0.115.8
+Requires-Dist: pydantic==2.11.7
+Requires-Dist: pydantic-settings==2.10.1
+Requires-Dist: fastapi[standard]==0.115.14
 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
-Requires-Dist: langchain-openai==0.3.16
+Requires-Dist: langchain==0.3.26
+Requires-Dist: langchain-community==0.3.26
+Requires-Dist: langchain-core==0.3.67
+Requires-Dist: langchain-openai==0.3.27
 Requires-Dist: langchain-anthropic==0.3.6
 Requires-Dist: langchain-google-genai==2.0.7
-Requires-Dist: langchain-google-vertexai==2.0.13
-Requires-Dist: langchain-groq==0.3.2
-Requires-Dist: langchain-ollama==0.3.2
-Requires-Dist: faiss-cpu==1.9.0
-Requires-Dist: chromadb==0.6.3
-Requires-Dist: langchain_chroma==0.2.1
-Requires-Dist: fastembed==0.5.1
+Requires-Dist: langchain-google-vertexai==2.0.27
+Requires-Dist: langchain-groq==0.3.5
+Requires-Dist: langchain-ollama==0.3.3
+Requires-Dist: faiss-cpu==1.11.0
+Requires-Dist: chromadb==1.0.13
+Requires-Dist: langchain_chroma==0.2.4
+Requires-Dist: fastembed==0.7.1
 Requires-Dist: langchain-qdrant==0.2.0
 Requires-Dist: lark==1.2.2
 Requires-Dist: unstructured==0.16.21
@@ -48,9 +47,10 @@ Requires-Dist: unstructured-ingest[sftp]
 Requires-Dist: unstructured-ingest[sharepoint]
 Requires-Dist: unstructured-ingest[slack]
 Requires-Dist: html5lib==1.1
-Requires-Dist: markdownify==0.14.1
+Requires-Dist: markdownify==1.1.0
 Requires-Dist: duckduckgo-search==8.0.4
 Requires-Dist: langchain_google_community==2.0.7
+Requires-Dist: trafilatura==2.0.0
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier

{ws_bom_robot_app-0.0.60 → ws_bom_robot_app-0.0.62}/requirements.txt

@@ -2,32 +2,30 @@
 standardwebhooks==1.0.0
 apscheduler==3.11.0
 aiofiles==24.1.0
-pydantic==2.10.6
-pydantic-settings==2.7.1
-fastapi[standard]==0.115.8
+pydantic==2.11.7
+pydantic-settings==2.10.1
+fastapi[standard]==0.115.14
 chevron==0.14.0
-trafilatura==2.0.0
 
 #framework
-langchain==0.3.25
-langchain-community==0.3.24
-langchain-core==0.3.59
-langchain-openai==0.3.16
+langchain==0.3.26
+langchain-community==0.3.26
+langchain-core==0.3.67
+langchain-openai==0.3.27
 langchain-anthropic==0.3.6 #issue get_models() from 0.3.7
 langchain-google-genai==2.0.7 #waiting for new release: https://github.com/langchain-ai/langchain-google/issues/711
-langchain-google-vertexai==2.0.13
-langchain-groq==0.3.2
-langchain-ollama==0.3.2
+langchain-google-vertexai==2.0.27
+langchain-groq==0.3.5
+langchain-ollama==0.3.3
 
 #vector DB
-faiss-cpu==1.9.0
-chromadb==0.6.3
-langchain_chroma==0.2.1
-fastembed==0.5.1 #qdrant sparse embedding
+faiss-cpu==1.11.0
+chromadb==1.0.13
+langchain_chroma==0.2.4
+fastembed==0.7.1 #qdrant sparse embedding
 langchain-qdrant==0.2.0
 lark==1.2.2 #self-query retriever
 
-
 #loaders
 unstructured==0.16.21
 unstructured[image]
@@ -46,6 +44,9 @@ unstructured-ingest[slack]
 html5lib==1.1 #beautifulsoup4 parser
 
 #integrations
-markdownify==0.14.1 #sitemap
+markdownify==1.1.0 #sitemap
+
+##tools
 duckduckgo-search==8.0.4
 langchain_google_community==2.0.7
+trafilatura==2.0.0

{ws_bom_robot_app-0.0.60 → ws_bom_robot_app-0.0.62}/setup.py

@@ -4,7 +4,7 @@ _requirements = [line.split('#')[0].strip() for line in open("requirements.txt")
 
 setup(
     name="ws_bom_robot_app",
-    version="0.0.60",
+    version="0.0.62",
     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",

{ws_bom_robot_app-0.0.60 → ws_bom_robot_app-0.0.62}/ws_bom_robot_app/config.py

@@ -4,6 +4,7 @@ from pydantic_settings import BaseSettings
 import os
 
 class Settings(BaseSettings):
+    USER_AGENT: str = 'ws-bom-robot'
     robot_env: str = 'local'
     robot_user: str = 'user'
     robot_password: str = 'password'
@@ -28,7 +29,6 @@ class Settings(BaseSettings):
     GOOGLE_API_KEY: str = ''
     NEBULY_API_URL: str =''
     GOOGLE_APPLICATION_CREDENTIALS: str = '' # path to google credentials iam file, e.d. ./.secrets/google-credentials.json
-    TAVILY_API_KEY: str = '' #TODO DELETE
     model_config = ConfigDict(
         env_file='./.env',
         extra='ignore',
@@ -36,6 +36,7 @@ class Settings(BaseSettings):
     )
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
+        os.environ["USER_AGENT"] = self.USER_AGENT
         os.environ["OPENAI_API_KEY"] = self.OPENAI_API_KEY
         os.environ["OLLAMA_API_URL"] = self.OLLAMA_API_URL
         os.environ["ANTHROPIC_API_KEY"] = self.ANTHROPIC_API_KEY
@@ -44,8 +45,6 @@ class Settings(BaseSettings):
         os.environ["GOOGLE_API_KEY"] = self.GOOGLE_API_KEY
         os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = self.GOOGLE_APPLICATION_CREDENTIALS
         os.environ["NEBULY_API_URL"] = self.NEBULY_API_URL
-        # TODO DELETE
-        os.environ["TAVILY_API_KEY"] = self.TAVILY_API_KEY
 
     class RuntimeOptions(BaseModel):
         @staticmethod

{ws_bom_robot_app-0.0.60 → ws_bom_robot_app-0.0.62}/ws_bom_robot_app/cron_manager.py

@@ -59,14 +59,14 @@ class CronManager:
             Job('cleanup-task',task_manager.cleanup_task, interval=5 * 60),
             Job('cleanup-data',kb_cleanup_data_file, interval=180 * 60),
         ]
-    def __get_jobstore_strategy() -> JobstoreStrategy:
+    def __get_jobstore_strategy(self) -> JobstoreStrategy:
         if True or config.runtime_options().is_multi_process:
             return MemoryJobstoreStrategy()
         return PersistentJobstoreStrategy()
     def __init__(self, strategy: JobstoreStrategy = None, enable_defaults: bool = True):
         self.enable_defaults = enable_defaults
         if strategy is None:
-          strategy = CronManager.__get_jobstore_strategy()
+          strategy = self.__get_jobstore_strategy()
         jobstores = strategy.get_jobstore()
         self.scheduler: BackgroundScheduler = BackgroundScheduler(jobstores=jobstores)
         self.__scheduler_is_running = False

{ws_bom_robot_app-0.0.60 → ws_bom_robot_app-0.0.62}/ws_bom_robot_app/llm/agent_description.py

@@ -1,123 +1,123 @@
-import json, requests, re
-from typing import Any
-from abc import ABC, abstractmethod
-from langchain_core.prompts import ChatPromptTemplate
-from langchain_core.messages import AIMessage
-from langchain_core.runnables import RunnableSerializable
-from langchain_core.runnables import RunnableLambda
-from bs4 import BeautifulSoup
-from ws_bom_robot_app.llm.models.api import LlmRules
-from ws_bom_robot_app.llm.providers.llm_manager import LlmInterface
-from ws_bom_robot_app.llm.utils.agent import get_rules
-
-# SafeDict helper class
-class SafeDict(dict):
-    def __missing__(self, key):
-        return ''
-
-# Strategy Interface
-class AgentDescriptorStrategy(ABC):
-    @abstractmethod
-    def enrich_prompt(self, prompt: str, input: dict) -> str:
-        pass
-
-    @abstractmethod
-    def rule_input(self, input: dict) -> str:
-        pass
-
-# Concrete Strategy for Default Agent
-class DefaultAgentDescriptor(AgentDescriptorStrategy):
-    def enrich_prompt(self, prompt: str, input: dict) -> str:
-        # Default enrichment logic (could be minimal or no-op)
-        return prompt.format_map(SafeDict(input))
-
-    def rule_input(self, input: dict) -> str:
-        return input.get('content', "")
-
-# Concrete Strategy for URL2Text Agent
-class URL2TextAgentDescriptor(AgentDescriptorStrategy):
-    def enrich_prompt(self, prompt: str, input: dict) -> str:
-        input["context"] = self._get_page_text(input)
-        return prompt.format_map(SafeDict(input))
-
-    def rule_input(self, input: dict) -> str:
-        return input.get('context', "")
-
-    def _get_page_text(self, input: dict) -> str:
-        url = input.get("content", "")
-        exclusions = input.get("exclude", {})
-        response = requests.get(url)
-        response.raise_for_status()
-        soup = BeautifulSoup(response.content, 'html5lib')
-        classes_to_exclude = exclusions.get("classes", [])
-        ids_to_exclude = exclusions.get("ids", [])
-        for class_name in classes_to_exclude:
-            for element in soup.find_all(class_=class_name):
-                element.extract()
-        for id_name in ids_to_exclude:
-            for element in soup.find_all(id=id_name):
-                element.extract()
-        for script in soup(["script", "noscript", "style", "head", "footer", "iframe"]):
-            script.extract()
-        return re.sub(' +', ' ', soup.get_text())
-
-
-class AgentDescriptor:
-    # Dictionary to hold all agent strategies
-    _list: dict[str,AgentDescriptorStrategy] = {
-        "default": DefaultAgentDescriptor(),
-        "url2text": URL2TextAgentDescriptor(),
-    }
-
-    # Functions to manage strategies
-    @staticmethod
-    def add_strategy(name: str, strategy: AgentDescriptorStrategy):
-        """_summary_
-            add a new strategy to the dictionary
-        Args:
-            name (str): name of the strategy, in lowercase
-            strategy (AgentDescriptorStrategy): class implementing the strategy
-        Examples:
-            AgentDescriptor.add_strategy("custom_agent_descriptor", CustomAgentDescriptor())
-        """
-        AgentDescriptor._list[name.lower()] = strategy
-
-    @staticmethod
-    def get_strategy(name: str) -> AgentDescriptorStrategy:
-        return AgentDescriptor._list.get(name.lower(), DefaultAgentDescriptor())
-
-    def __init__(self, llm: LlmInterface, prompt: str, mode: str, rules: LlmRules = None):
-        self.__prompt = prompt
-        self.__llm = llm
-        self.rules= rules
-        self.strategy = self.get_strategy(mode)  # Selects the strategy from the dictionary
-
-    async def __create_prompt(self, input_dict: dict):
-        input_data = json.loads(input_dict.get("input", {}))
-        system = self.strategy.enrich_prompt(self.__prompt, input_data)
-        if self.rules:
-            rule_input = self.strategy.rule_input(input_data)
-            rules_prompt = await get_rules(self.__llm.get_embeddings(), self.rules, rule_input)
-            system += rules_prompt
-        return ChatPromptTemplate.from_messages(
-            [
-                ("system", system),
-                ("user", input_data.get("content", ""))
-            ]
-        )
-
-    def __create_agent_descriptor(self, content) -> RunnableSerializable[Any, Any]:
-        content = json.loads(content)
-        agent = (
-            {
-                "input": lambda x: x["input"],
-            }
-            | RunnableLambda(self.__create_prompt)
-            | self.__llm.get_llm()
-        )
-        return agent
-
-    async def run_agent(self, content) -> Any:
-        agent_descriptor = self.__create_agent_descriptor(content)
-        response: AIMessage = await agent_descriptor.ainvoke({"input": content})
-        return response
+import json, requests, re
+from typing import Any
+from abc import ABC, abstractmethod
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.messages import AIMessage
+from langchain_core.runnables import RunnableSerializable
+from langchain_core.runnables import RunnableLambda
+from bs4 import BeautifulSoup
+from ws_bom_robot_app.llm.models.api import LlmRules
+from ws_bom_robot_app.llm.providers.llm_manager import LlmInterface
+from ws_bom_robot_app.llm.utils.agent import get_rules
+
+# SafeDict helper class
+class SafeDict(dict):
+    def __missing__(self, key):
+        return ''
+
+# Strategy Interface
+class AgentDescriptorStrategy(ABC):
+    @abstractmethod
+    def enrich_prompt(self, prompt: str, input: dict) -> str:
+        pass
+
+    @abstractmethod
+    def rule_input(self, input: dict) -> str:
+        pass
+
+# Concrete Strategy for Default Agent
+class DefaultAgentDescriptor(AgentDescriptorStrategy):
+    def enrich_prompt(self, prompt: str, input: dict) -> str:
+        # Default enrichment logic (could be minimal or no-op)
+        return prompt.format_map(SafeDict(input))
+
+    def rule_input(self, input: dict) -> str:
+        return input.get('content', "")
+
+# Concrete Strategy for URL2Text Agent
+class URL2TextAgentDescriptor(AgentDescriptorStrategy):
+    def enrich_prompt(self, prompt: str, input: dict) -> str:
+        input["context"] = self._get_page_text(input)
+        return prompt.format_map(SafeDict(input))
+
+    def rule_input(self, input: dict) -> str:
+        return input.get('context', "")
+
+    def _get_page_text(self, input: dict) -> str:
+        url = input.get("content", "")
+        exclusions = input.get("exclude", {})
+        response = requests.get(url)
+        response.raise_for_status()
+        soup = BeautifulSoup(response.content, 'html5lib')
+        classes_to_exclude = exclusions.get("classes", [])
+        ids_to_exclude = exclusions.get("ids", [])
+        for class_name in classes_to_exclude:
+            for element in soup.find_all(class_=class_name):
+                element.extract()
+        for id_name in ids_to_exclude:
+            for element in soup.find_all(id=id_name):
+                element.extract()
+        for script in soup(["script", "noscript", "style", "head", "footer", "iframe"]):
+            script.extract()
+        return re.sub(' +', ' ', soup.get_text())
+
+
+class AgentDescriptor:
+    # Dictionary to hold all agent strategies
+    _list: dict[str,AgentDescriptorStrategy] = {
+        "default": DefaultAgentDescriptor(),
+        "url2text": URL2TextAgentDescriptor(),
+    }
+
+    # Functions to manage strategies
+    @staticmethod
+    def add_strategy(name: str, strategy: AgentDescriptorStrategy):
+        """_summary_
+            add a new strategy to the dictionary
+        Args:
+            name (str): name of the strategy, in lowercase
+            strategy (AgentDescriptorStrategy): class implementing the strategy
+        Examples:
+            AgentDescriptor.add_strategy("custom_agent_descriptor", CustomAgentDescriptor())
+        """
+        AgentDescriptor._list[name.lower()] = strategy
+
+    @staticmethod
+    def get_strategy(name: str) -> AgentDescriptorStrategy:
+        return AgentDescriptor._list.get(name.lower(), DefaultAgentDescriptor())
+
+    def __init__(self, llm: LlmInterface, prompt: str, mode: str, rules: LlmRules = None):
+        self.__prompt = prompt
+        self.__llm = llm
+        self.rules= rules
+        self.strategy = self.get_strategy(mode)  # Selects the strategy from the dictionary
+
+    async def __create_prompt(self, input_dict: dict):
+        input_data = json.loads(input_dict.get("input", {}))
+        system = self.strategy.enrich_prompt(self.__prompt, input_data)
+        if self.rules:
+            rule_input = self.strategy.rule_input(input_data)
+            rules_prompt = await get_rules(self.__llm.get_embeddings(), self.rules, rule_input)
+            system += rules_prompt
+        return ChatPromptTemplate.from_messages(
+            [
+                ("system", system),
+                ("user", input_data.get("content", ""))
+            ]
+        )
+
+    def __create_agent_descriptor(self, content) -> RunnableSerializable[Any, Any]:
+        content = json.loads(content)
+        agent = (
+            {
+                "input": lambda x: x["input"],
+            }
+            | RunnableLambda(self.__create_prompt)
+            | self.__llm.get_llm()
+        )
+        return agent
+
+    async def run_agent(self, content) -> Any:
+        agent_descriptor = self.__create_agent_descriptor(content)
+        response: AIMessage = await agent_descriptor.ainvoke({"input": content})
+        return response