ws-bom-robot-app 0.0.68__tar.gz → 0.0.70__tar.gz

{ws_bom_robot_app-0.0.68/ws_bom_robot_app.egg-info → ws_bom_robot_app-0.0.70}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ws_bom_robot_app
-Version: 0.0.68
+Version: 0.0.70
 Summary: A FastAPI application serving ws bom/robot/llm platform ai.
 Home-page: https://github.com/websolutespa/bom
 Author: Websolute Spa
@@ -258,11 +258,17 @@ docker build -f Dockerfile-robot-base-gpu -t ghcr.io/websolutespa/ws-bom-robot-b
 docker push ghcr.io/websolutespa/ws-bom-robot-base:gpu
 ```
 
-dockerize app from src
+dockerize app
 
 ```pwsh
-docker build -f Dockerfile-src -t ws-bom-robot-app:src .
-docker run --name ws-bom-robot-app-src -d -v "$(pwd)/ws_bom_robot_app:/app/ws_bom_robot_app" -v "$(pwd)/.data:/app/.data" -v "$(pwd)/tests:/app/tests" -v "$(pwd)/tmp:/tmp"  -p 6002:6001 ws-bom-robot-app:src
+docker build -f Dockerfile -t ws-bom-robot-app .
+docker run --rm --name ws-bom-robot-app -d -p 6001:6001 ws-bom-robot-app
+```
+
+docker run mounted to src
+
+```pwsh
+docker run --rm --name ws-bom-robot-app-src -d -v "$(pwd)/ws_bom_robot_app:/app/ws_bom_robot_app" -v "$(pwd)/.data:/app/.data" -v "$(pwd)/tmp:/tmp"  -p 6001:6001 ws-bom-robot-app
 ```
 
 ### ✈️ publish

{ws_bom_robot_app-0.0.68 → ws_bom_robot_app-0.0.70}/README.md

@@ -193,11 +193,17 @@ docker build -f Dockerfile-robot-base-gpu -t ghcr.io/websolutespa/ws-bom-robot-b
 docker push ghcr.io/websolutespa/ws-bom-robot-base:gpu
 ```
 
-dockerize app from src
+dockerize app
 
 ```pwsh
-docker build -f Dockerfile-src -t ws-bom-robot-app:src .
-docker run --name ws-bom-robot-app-src -d -v "$(pwd)/ws_bom_robot_app:/app/ws_bom_robot_app" -v "$(pwd)/.data:/app/.data" -v "$(pwd)/tests:/app/tests" -v "$(pwd)/tmp:/tmp"  -p 6002:6001 ws-bom-robot-app:src
+docker build -f Dockerfile -t ws-bom-robot-app .
+docker run --rm --name ws-bom-robot-app -d -p 6001:6001 ws-bom-robot-app
+```
+
+docker run mounted to src
+
+```pwsh
+docker run --rm --name ws-bom-robot-app-src -d -v "$(pwd)/ws_bom_robot_app:/app/ws_bom_robot_app" -v "$(pwd)/.data:/app/.data" -v "$(pwd)/tmp:/tmp"  -p 6001:6001 ws-bom-robot-app
 ```
 
 ### ✈️ publish

{ws_bom_robot_app-0.0.68 → ws_bom_robot_app-0.0.70}/setup.py

@@ -4,7 +4,7 @@ _requirements = [line.split('#')[0].strip() for line in open("requirements.txt")
 
 setup(
     name="ws_bom_robot_app",
-    version="0.0.68",
+    version="0.0.70",
     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-0.0.68 → ws_bom_robot_app-0.0.70}/ws_bom_robot_app/llm/providers/llm_manager.py

@@ -107,9 +107,8 @@ class Google(LlmInterface):
   def get_llm(self):
     from langchain_google_genai.chat_models import ChatGoogleGenerativeAI
     return ChatGoogleGenerativeAI(
-      name="chat",
-      api_key=self.config.api_key or os.getenv("GOOGLE_API_KEY"),
       model=self.config.model,
+      google_api_key=self.config.api_key or os.getenv("GOOGLE_API_KEY"),
       temperature=self.config.temperature,
       disable_streaming=False,
     )
@@ -117,8 +116,8 @@ class Google(LlmInterface):
   def get_embeddings(self):
     from langchain_google_genai.embeddings import GoogleGenerativeAIEmbeddings
     return GoogleGenerativeAIEmbeddings(
-      google_api_key=self.config.api_key,
-      model="models/text-embedding-005")
+      google_api_key=self.config.api_key or os.getenv("GOOGLE_API_KEY"),
+      model="models/text-embedding-004")
 
   def get_models(self):
     import google.generativeai as genai
@@ -140,22 +139,33 @@ class Gvertex(LlmInterface):
             temperature=self.config.temperature
         )
     def get_embeddings(self):
-        from langchain_google_vertexai import VertexAIEmbeddings
-        return VertexAIEmbeddings(model_name="text-embedding-005")
+        from langchain_google_vertexai.embeddings import VertexAIEmbeddings
+        embeddings = VertexAIEmbeddings(model_name="text-embedding-004")
+        #fix gemini-embedding-001 batch size
+        #embeddings.instance["max_batch_size"] = 1
+        #embeddings.instance["batch_size"] = 1
+        return embeddings
     def get_models(self):
-        #from google.cloud import aiplatform
-        #aiplatform.init()
-        #models = aiplatform.Model.list()
+        _models = [
+                {"id":"gemini-2.5-pro"},
+                {"id":"gemini-2.5-flash"},
+                {"id":"gemini-2.0-flash"},
+                {"id":"gemini-2.0-flash-lite"}
+              ]
+        try:
+          from google.cloud import aiplatform
+          aiplatform.init()
+          _list = aiplatform.Model.list()
+          if _list:
+            _models = list([{"id": model.name} for model in _list])
         # removed due issue: https://github.com/langchain-ai/langchain-google/issues/733
         # Message type "google.cloud.aiplatform.v1beta1.GenerateContentResponse" has no field named "createTime" at "GenerateContentResponse".  Available Fields(except extensions): "['candidates', 'modelVersion', 'promptFeedback', 'usageMetadata']"
-
-        #see https://cloud.google.com/vertex-ai/generative-ai/docs/learn/locations#united-states for available models
-        return [
-              {"id":"gemini-2.5-pro-preview-05-06"},
-              {"id":"gemini-2.0-flash"},
-              {"id":"gemini-2.0-flash-lite"},
-              {"id":"gemini-1.5-pro-002"}
-            ]
+        except Exception as e:
+          print(f"Error fetching models from Gvertex: {e}")
+          # fallback to hardcoded models
+          #see https://cloud.google.com/vertex-ai/generative-ai/docs/learn/locations#united-states for available models
+        finally:
+          return _models
 
 class Groq(LlmInterface):
     def get_llm(self):

{ws_bom_robot_app-0.0.68 → ws_bom_robot_app-0.0.70}/ws_bom_robot_app/llm/vector_store/integration/manager.py

@@ -12,7 +12,7 @@ from ws_bom_robot_app.llm.vector_store.integration.sftp import Sftp
 from ws_bom_robot_app.llm.vector_store.integration.sharepoint import Sharepoint
 from ws_bom_robot_app.llm.vector_store.integration.sitemap import Sitemap
 from ws_bom_robot_app.llm.vector_store.integration.slack import Slack
-
+from ws_bom_robot_app.llm.vector_store.integration.thron import Thron
 class IntegrationManager:
   _list: dict[str, Type[IntegrationStrategy]] = {
     "llmkbazure": Azure,
@@ -27,7 +27,7 @@ class IntegrationManager:
     "llmkbsharepoint": Sharepoint,
     "llmkbsitemap": Sitemap,
     "llmkbslack": Slack,
-
+    "llmkbthron": Thron,
   }
   @classmethod
   def get_strategy(cls, name: str, knowledgebase_path: str, data: dict[str, str]) -> IntegrationStrategy:

ws_bom_robot_app-0.0.70/ws_bom_robot_app/llm/vector_store/integration/thron.py

@@ -0,0 +1,123 @@
+import asyncio, logging, aiohttp
+from ws_bom_robot_app.llm.vector_store.integration.base import IntegrationStrategy, UnstructuredIngest
+from unstructured_ingest.v2.processes.connectors.fsspec.sftp import SftpConnectionConfig, SftpAccessConfig, SftpDownloaderConfig, SftpIndexerConfig
+from langchain_core.documents import Document
+from ws_bom_robot_app.llm.vector_store.loader.base import Loader
+from typing import List, Union, Optional
+from pydantic import BaseModel, Field, AliasChoices
+import json
+import os
+
+class ThronParams(BaseModel):
+  """
+  ThronParams is a model that defines the parameters required for Thron integration.
+
+  Attributes:
+    app_id (str): The application ID for Thron.
+    client_id (str): The client ID for Thron.
+    client_secret (str): The client secret for Thron.
+  """
+  organization_name: str = Field(validation_alias=AliasChoices("organizationName","organization_name"))
+  attribute_fields: Optional[List[str]] = Field(default=None, validation_alias=AliasChoices("attributeFields","attribute_fields"))
+  client_id: str = Field(validation_alias=AliasChoices("clientId","client_id"))
+  client_secret: str = Field(validation_alias=AliasChoices("clientSecret","client_secret"))
+
+class Thron(IntegrationStrategy):
+  def __init__(self, knowledgebase_path: str, data: dict[str, Union[str,int,list]]):
+    super().__init__(knowledgebase_path, data)
+    self.__data = ThronParams.model_validate(self.data)
+
+  def working_subdirectory(self) -> str:
+    return 'thron'
+
+  async def run(self) -> None:
+    _data = await self.__get_data()
+    transformed_data = self.__transform_data(_data)
+    json_file_path = os.path.join(self.working_directory, 'thron_data.json')
+    with open(json_file_path, 'w', encoding='utf-8') as f:
+      json.dump(transformed_data, f, indent=2, ensure_ascii=False)
+
+  async def load(self) -> list[Document]:
+    await self.run()
+    await asyncio.sleep(1)
+    return await Loader(self.working_directory).load()
+
+  async def __get_auth_token(self) -> str:
+    try:
+      async with aiohttp.ClientSession() as session:
+        auth_data = {
+          "grant_type": "client_credentials",
+          "client_id": self.__data.client_id,
+          "client_secret": self.__data.client_secret
+        }
+        headers = {
+          "accept": "application/json",
+          "Content-Type": "application/x-www-form-urlencoded"
+        }
+        async with session.post("https://websolute.thron.com/api/v1/authentication/oauth2/token", data=auth_data, headers=headers) as response:
+          result = await response.json()
+          return result.get("access_token", "")
+    except Exception as e:
+      logging.error(f"Error fetching Thron auth token: {e}")
+      return None
+
+  async def __get_data(self) -> dict:
+    try:
+      token = await self.__get_auth_token()
+      if not token:
+        logging.error("Failed to obtain Thron authentication token.")
+        return {}
+      attribute_fields = ",".join(self.__data.attribute_fields) if self.__data.attribute_fields else ""
+      async with aiohttp.ClientSession() as session:
+        headers = {
+          "accept": "application/json",
+          "Authorization": f"Bearer {token}"
+        }
+        async with session.get(f"https://{self.__data.organization_name}.thron.com/api/v1/product-data/products?attributeFields=product_id,{attribute_fields}", headers=headers) as response:
+          result = await response.json()
+          return result.get("items", {})
+    except Exception as e:
+      logging.error(f"Error fetching Thron product data: {e}")
+      return {}
+    return []
+
+
+
+  def __transform_data(self, data: dict) -> dict:
+    transformed_data = []
+
+    # First pass: collect all MASTER items
+    master_items = {item.get("id"): item for item in data if item.get("hierarchyLevel") == "MASTER"}
+
+    # Second pass: process items
+    for item in data:
+      hierarchy_level = item.get("hierarchyLevel")
+
+      if hierarchy_level == "MASTER":
+        # Find matching variants for this master
+        master_id = item.get("id")
+        item_copy = item.copy()
+        item_copy["variants"] = []
+
+        # Look for variants that belong to this master
+        for variant_item in data:
+          if (variant_item.get("hierarchyLevel") == "VARIANT" and
+            variant_item.get("variation", {}).get("master")):
+
+            variant_master_id = variant_item.get("variation").get("master").split(":")[-1]
+
+            # Check if this variant belongs to current master by comparing product_ids
+            for attr in item.get("attributes", []):
+              if (attr.get("code") == "product_id" and
+                attr.get("identifier") == variant_master_id):
+                item_copy["variants"].append(variant_item)
+                break
+
+        # Only add master items that have variants
+        if item_copy["variants"]:
+          transformed_data.append(item_copy)
+
+      elif hierarchy_level == "SIMPLE":
+        transformed_data.append(item)
+
+    return transformed_data

{ws_bom_robot_app-0.0.68 → ws_bom_robot_app-0.0.70/ws_bom_robot_app.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ws_bom_robot_app
-Version: 0.0.68
+Version: 0.0.70
 Summary: A FastAPI application serving ws bom/robot/llm platform ai.
 Home-page: https://github.com/websolutespa/bom
 Author: Websolute Spa
@@ -258,11 +258,17 @@ docker build -f Dockerfile-robot-base-gpu -t ghcr.io/websolutespa/ws-bom-robot-b
 docker push ghcr.io/websolutespa/ws-bom-robot-base:gpu
 ```
 
-dockerize app from src
+dockerize app
 
 ```pwsh
-docker build -f Dockerfile-src -t ws-bom-robot-app:src .
-docker run --name ws-bom-robot-app-src -d -v "$(pwd)/ws_bom_robot_app:/app/ws_bom_robot_app" -v "$(pwd)/.data:/app/.data" -v "$(pwd)/tests:/app/tests" -v "$(pwd)/tmp:/tmp"  -p 6002:6001 ws-bom-robot-app:src
+docker build -f Dockerfile -t ws-bom-robot-app .
+docker run --rm --name ws-bom-robot-app -d -p 6001:6001 ws-bom-robot-app
+```
+
+docker run mounted to src
+
+```pwsh
+docker run --rm --name ws-bom-robot-app-src -d -v "$(pwd)/ws_bom_robot_app:/app/ws_bom_robot_app" -v "$(pwd)/.data:/app/.data" -v "$(pwd)/tmp:/tmp"  -p 6001:6001 ws-bom-robot-app
 ```
 
 ### ✈️ publish

{ws_bom_robot_app-0.0.68 → ws_bom_robot_app-0.0.70}/ws_bom_robot_app.egg-info/SOURCES.txt

@@ -72,6 +72,7 @@ ws_bom_robot_app/llm/vector_store/integration/sftp.py
 ws_bom_robot_app/llm/vector_store/integration/sharepoint.py
 ws_bom_robot_app/llm/vector_store/integration/sitemap.py
 ws_bom_robot_app/llm/vector_store/integration/slack.py
+ws_bom_robot_app/llm/vector_store/integration/thron.py
 ws_bom_robot_app/llm/vector_store/loader/__init__.py
 ws_bom_robot_app/llm/vector_store/loader/base.py
 ws_bom_robot_app/llm/vector_store/loader/docling.py