ws-bom-robot-app 0.0.29__tar.gz → 0.0.31__tar.gz

ws_bom_robot_app-0.0.31/MANIFEST.in

@@ -0,0 +1,2 @@
+include requirements.txt
+include README.md

{ws_bom_robot_app-0.0.29 → ws_bom_robot_app-0.0.31}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ws_bom_robot_app
-Version: 0.0.29
+Version: 0.0.31
 Summary: A FastAPI application serving ws bom/robot/llm platform ai.
 Home-page: https://github.com/websolutespa/bom
 Author: Websolute Spa
@@ -13,17 +13,17 @@ 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==2.10.3
-Requires-Dist: pydantic-settings==2.6.1
-Requires-Dist: fastapi[standard]==0.115.5
-Requires-Dist: langchain==0.3.9
-Requires-Dist: langchain-openai==0.2.10
-Requires-Dist: langchain-community==0.3.8
-Requires-Dist: langchain-core==0.3.21
+Requires-Dist: pydantic==2.10.5
+Requires-Dist: pydantic-settings==2.7.1
+Requires-Dist: fastapi[standard]==0.115.6
+Requires-Dist: langchain==0.3.14
+Requires-Dist: langchain-openai==0.3.0
+Requires-Dist: langchain-community==0.3.14
+Requires-Dist: langchain-core==0.3.29
 Requires-Dist: faiss-cpu==1.9.0
-Requires-Dist: unstructured==0.16.11
+Requires-Dist: unstructured==0.16.13
 Requires-Dist: unstructured[image]
-Requires-Dist: unstructured-ingest==0.3.8
+Requires-Dist: unstructured-ingest==0.3.14
 Requires-Dist: unstructured-ingest[azure]
 Requires-Dist: unstructured-ingest[confluence]
 Requires-Dist: unstructured-ingest[dropbox]
@@ -37,7 +37,7 @@ Requires-Dist: unstructured-ingest[sharepoint]
 Requires-Dist: unstructured-ingest[slack]
 Requires-Dist: html5lib==1.1
 Requires-Dist: markdownify==0.14.1
-Requires-Dist: nebuly==0.3.35
+Requires-Dist: nebuly==0.3.36
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier
@@ -185,10 +185,7 @@ py -m pip install --upgrade setuptools build twine streamlit
 ### 🪛 build
 
 ```pwsh
-if (Test-Path ./dist) {rm ./dist -r -force}; `
-cp .\requirements.txt .\ws_bom_robot_app\ && `
-py -m build && `
-twine check dist/*
+py -m build && twine check dist/*
 ```
 
 ### 📦 test / 🧪 debugger

{ws_bom_robot_app-0.0.29 → ws_bom_robot_app-0.0.31}/README.md

@@ -135,10 +135,7 @@ py -m pip install --upgrade setuptools build twine streamlit
 ### 🪛 build
 
 ```pwsh
-if (Test-Path ./dist) {rm ./dist -r -force}; `
-cp .\requirements.txt .\ws_bom_robot_app\ && `
-py -m build && `
-twine check dist/*
+py -m build && twine check dist/*
 ```
 
 ### 📦 test / 🧪 debugger

{ws_bom_robot_app-0.0.29 → ws_bom_robot_app-0.0.31}/pyproject.toml

@@ -1,5 +1,5 @@
 [build-system]
-requires = ["setuptools >= 64"]
+requires = ["setuptools >= 75"]
 build-backend = "setuptools.build_meta"
 
 [tool.pytest.ini_options]

{ws_bom_robot_app-0.0.29/ws_bom_robot_app → ws_bom_robot_app-0.0.31}/requirements.txt

@@ -2,15 +2,15 @@
 standardwebhooks==1.0.0
 apscheduler==3.11.0
 aiofiles==24.1.0
-pydantic==2.10.3
-pydantic-settings==2.6.1
-fastapi[standard]==0.115.5
+pydantic==2.10.5
+pydantic-settings==2.7.1
+fastapi[standard]==0.115.6
 
 #framework
-langchain==0.3.9
-langchain-openai==0.2.10
-langchain-community==0.3.8
-langchain-core==0.3.21
+langchain==0.3.14
+langchain-openai==0.3.0
+langchain-community==0.3.14
+langchain-core==0.3.29
 
 #vector DB
 faiss-cpu==1.9.0
@@ -20,11 +20,11 @@ faiss-cpu==1.9.0
 #loaders
 #python-magic==0.4.27
 #opencv-python-headless==4.10.0.84 #docker specs
-unstructured==0.16.11
+unstructured==0.16.13
 unstructured[image]
 #unstructured[all-docs]==0.16.11
 #langchain_unstructured==0.1.5
-unstructured-ingest==0.3.8
+unstructured-ingest==0.3.14
 unstructured-ingest[azure]
 unstructured-ingest[confluence]
 unstructured-ingest[dropbox]
@@ -42,4 +42,4 @@ html5lib==1.1 #beautifulsoup4 parser
 markdownify==0.14.1 #sitemap
 
 #telemetry
-nebuly==0.3.35
+nebuly==0.3.36

{ws_bom_robot_app-0.0.29 → ws_bom_robot_app-0.0.31}/setup.py

@@ -1,8 +1,10 @@
 from setuptools import setup, find_packages
 
+_requirements = [line.split('#')[0].strip() for line in open("requirements.txt").readlines() if all([line.strip(), not line.startswith("#")])]
+
 setup(
     name="ws_bom_robot_app",
-    version="0.0.29",
+    version="0.0.31",
     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",
@@ -10,7 +12,7 @@ setup(
     author_email="dev@websolute.it",
     url="https://github.com/websolutespa/bom",
     packages=find_packages(),
-    install_requires=[line.split('#')[0].strip() for line in open("ws_bom_robot_app/requirements.txt").readlines() if all([line.strip(), not line.startswith("#")])],
+    install_requires=_requirements,
     classifiers=[
         "Programming Language :: Python :: 3",
         "License :: OSI Approved :: MIT License",
@@ -18,4 +20,3 @@ setup(
     ],
     python_requires=">=3.12",
 )
-

{ws_bom_robot_app-0.0.29 → ws_bom_robot_app-0.0.31}/ws_bom_robot_app/llm/agent_description.py

@@ -1,124 +1,124 @@
-import json, requests, re
-from typing import Any
-from abc import ABC, abstractmethod
-from langchain_openai import ChatOpenAI
-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.utils.agent_utils 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, api_key: str, prompt: str, mode: str, rules: LlmRules = None):
-        self.__prompt = prompt
-        self.__llm = ChatOpenAI(model="gpt-4o", temperature=0, api_key=api_key)  # type: ignore
-        self.api_key = api_key
-        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.rules,self.api_key, 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
-        )
-        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_openai import ChatOpenAI
+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.utils.agent_utils 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, api_key: str, prompt: str, mode: str, rules: LlmRules = None):
+        self.__prompt = prompt
+        self.__llm = ChatOpenAI(model="gpt-4o", temperature=0, api_key=api_key)  # type: ignore
+        self.api_key = api_key
+        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.rules,self.api_key, 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
+        )
+        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