ws-bom-robot-app 0.0.27__py3-none-any.whl → 0.0.29__py3-none-any.whl

ws_bom_robot_app/llm/main.py

@@ -11,6 +11,8 @@ from langchain_core.callbacks.base import AsyncCallbackHandler
 import warnings, asyncio, os, io, sys, json
 from typing import List
 from asyncio import Queue
+from langchain.callbacks.tracers import LangChainTracer
+from langsmith import Client as LangSmithClient
 
 async def invoke(rq: InvokeRequest) -> str:
   await rq.initialize()
@@ -52,22 +54,30 @@ async def __stream(rq: StreamRequest,queue: Queue,formatted: bool = True) -> Non
             message_content = message.content
           settings.chat_history.append(AIMessage(content=message_content))
 
+  if rq.lang_chain_tracing:
+    client = LangSmithClient(
+      api_key= rq.secrets.get("langChainApiKey", "")
+    )
+    trace = LangChainTracer(project_name=rq.lang_chain_project,client=client)
+    callbacks.append(trace)
+
   processor = AgentLcel(
       openai_config={"api_key": rq.secrets["openAIApiKey"], "openai_model": rq.model, "temperature": rq.temperature},
       sys_message=rq.system_message,
-      tools=get_structured_tools(tools=rq.app_tools, api_key=rq.secrets["openAIApiKey"], callbacks=[callbacks[0]], queue=queue),
+      tools=get_structured_tools(tools=rq.app_tools, api_key=rq.secrets["openAIApiKey"], callbacks=[callbacks], queue=queue),
       rules=rq.rules
   )
-
-  if "NEBULY_API_KEY" in os.environ:
+  if rq.secrets.get("nebulyApiKey","") != "":
     nebuly_callback = LangChainTrackingHandler(
-            api_key= os.environ["NEBULY_API_KEY"],
+            api_key= rq.secrets.get("nebulyApiKey"),
             user_id=rq.thread_id,
+            nebuly_tags={"project": rq.lang_chain_project},
         )
     callbacks.append(nebuly_callback)
 
   with warnings.catch_warnings():
     warnings.simplefilter("ignore", UserWarning)
+
     await processor.executor.ainvoke(
         {"input": rq.messages[-1], "chat_history": settings.chat_history},
         {"callbacks": callbacks},

ws_bom_robot_app/llm/models/api.py

@@ -90,14 +90,6 @@ class LlmApp(BaseModel):
           self.__decompress_zip(db_destination_file, db_folder)
         else:
           os.removedirs(db_folder)
-  def __update_envs(self) -> None:
-    _envs =  {
-          "LANGCHAIN_API_KEY": self.secrets.get("langChainApiKey", ""),
-          "LANGCHAIN_PROJECT": self.lang_chain_project or "",
-          "LANGCHAIN_TRACING_V2": str(self.lang_chain_tracing).lower(),
-          "NEBULY_API_KEY": self.secrets.get("nebulyApiKey", "")
-      }
-    os.environ.update({k: v for k, v in _envs.items() if v})
   def __normalize_vector_db_path(self) -> None:
     _vector_db_folder = self.__vector_db_folder()
     self.vector_db = os.path.join(_vector_db_folder, os.path.splitext(os.path.basename(self.vector_db))[0]) if self.vector_db else None
@@ -106,7 +98,6 @@ class LlmApp(BaseModel):
     for tool in self.app_tools or []:
       tool.vector_db = os.path.join(_vector_db_folder, os.path.splitext(os.path.basename(tool.vector_db))[0]) if tool.vector_db else None
   async def initialize(self) -> None:
-      self.__update_envs()
       await self.__extract_db()
       self.__normalize_vector_db_path()
 

ws_bom_robot_app/llm/vector_store/loader/base.py

@@ -8,8 +8,15 @@ from pydantic import BaseModel
 from ws_bom_robot_app.config import config
 from ws_bom_robot_app.llm.vector_store.loader.json_loader import JsonLoader
 from ws_bom_robot_app.llm.vector_store.loader.docling import DoclingLoader
-from langchain_community.document_loaders import CSVLoader, UnstructuredPowerPointLoader, UnstructuredEmailLoader, UnstructuredXMLLoader, TextLoader, UnstructuredHTMLLoader
-
+from langchain_community.document_loaders import (
+    BSHTMLLoader,
+    CSVLoader,
+    UnstructuredEmailLoader,
+    UnstructuredImageLoader,
+    UnstructuredXMLLoader,
+    UnstructuredPowerPointLoader,
+    TextLoader
+    )
 class LoaderConfig(BaseModel):
   loader: type[BaseLoader]
   kwargs: Optional[dict[str, Any]] = {}
@@ -39,12 +46,12 @@ class Loader():
     '.tsv': None,
     '.text': None,
     '.log': None,
-    '.htm': LoaderConfig(loader=UnstructuredHTMLLoader,kwargs={"strategy":"auto"}),
-    '.html': LoaderConfig(loader=UnstructuredHTMLLoader,kwargs={"strategy":"auto"}),
+    '.htm': LoaderConfig(loader=BSHTMLLoader),
+    '.html': LoaderConfig(loader=BSHTMLLoader),
     ".pdf": LoaderConfig(loader=DoclingLoader),
-    '.png': LoaderConfig(loader=DoclingLoader),
-    '.jpg': LoaderConfig(loader=DoclingLoader),
-    '.jpeg': LoaderConfig(loader=DoclingLoader),
+    '.png': LoaderConfig(loader=UnstructuredImageLoader,kwargs={"strategy":"auto","mode":"single"}),
+    '.jpg': LoaderConfig(loader=UnstructuredImageLoader,kwargs={"strategy":"auto","mode":"single"}),
+    '.jpeg': LoaderConfig(loader=UnstructuredImageLoader,kwargs={"strategy":"auto","mode":"single"}),
     '.gif': None,
     ".emf": None,
     ".wmf": None,

ws_bom_robot_app/llm/vector_store/loader/docling.py

@@ -3,12 +3,16 @@ from typing import Iterator, AsyncIterator, Optional
 from langchain_core.document_loaders import BaseLoader
 from langchain_core.documents import Document
 from langchain_core.runnables import run_in_executor
-from docling.document_converter import DocumentConverter, ConversionResult, ConversionStatus
+from docling.document_converter import DocumentConverter, InputFormat, PdfFormatOption
+from docling.datamodel.pipeline_options import PdfPipelineOptions, TableStructureOptions, TableFormerMode
 
 class DoclingLoader(BaseLoader):
   def __init__(self, file_path: str | list[str]) -> None:
       self._file_paths = file_path if isinstance(file_path, list) else [file_path]
-      self._converter = DocumentConverter()
+      self._converter = DocumentConverter(format_options={
+            InputFormat.PDF: PdfFormatOption(pipeline_options=PdfPipelineOptions(
+              table_structure_options=TableStructureOptions(mode=TableFormerMode.ACCURATE)))
+        })
   def load(self) -> list[Document]:
       """Load data into Document objects."""
       return list(self.lazy_load())

{ws_bom_robot_app-0.0.27.dist-info → ws_bom_robot_app-0.0.29.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: ws_bom_robot_app
-Version: 0.0.27
+Version: 0.0.29
 Summary: A FastAPI application serving ws bom/robot/llm platform ai.
 Home-page: https://github.com/websolutespa/bom
 Author: Websolute Spa
@@ -38,6 +38,15 @@ Requires-Dist: unstructured-ingest[slack]
 Requires-Dist: html5lib==1.1
 Requires-Dist: markdownify==0.14.1
 Requires-Dist: nebuly==0.3.35
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
 
 # 🤖 ws-bom-robot-app
 
@@ -118,6 +127,14 @@ robot_cms_files_folder=llmKbFile
   }
   ```
 
+  #### docling
+  
+  Set the following environment variables
+
+  ```pwsh
+  KMP_DUPLICATE_LIB_OK=TRUE
+  ```    
+
   #### libreoffice (optional: for robot_env set to development/production)
 
   [Install libreoffice](https://www.libreoffice.org/download/download-libreoffice/)

{ws_bom_robot_app-0.0.27.dist-info → ws_bom_robot_app-0.0.29.dist-info}/RECORD

@@ -11,10 +11,10 @@ ws_bom_robot_app/llm/agent_handler.py,sha256=Qz3h1eZdA6pkurEbr8sQwl-0FdjugaO5Q9s
 ws_bom_robot_app/llm/agent_lcel.py,sha256=jkSLMy6y_ZFvWT8bhBBYHY5CO-ea8oMSPMXMahFUBFc,2666
 ws_bom_robot_app/llm/api.py,sha256=vBu_TFTlBjp7e3J-WmlZbXn_TbB550x-NpQN4YsO7To,3004
 ws_bom_robot_app/llm/defaut_prompt.py,sha256=pn5a4lNLWE1NngHYjA_7tD8GasePMgsgude5fIJxsW0,756
-ws_bom_robot_app/llm/main.py,sha256=_uW3Iy9iPJbxDfpyoReu3mbYY8a9dS1V6tZU-z6BELo,3547
+ws_bom_robot_app/llm/main.py,sha256=S4CSLxy3Rmtrl1e3F7yRJ1jz09MfyeFMXa7305ZJq4w,3943
 ws_bom_robot_app/llm/settings.py,sha256=EkFGCppORenStH9W4e6_dYvQ-5p6xiEMpmUHBqNqG9M,117
 ws_bom_robot_app/llm/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ws_bom_robot_app/llm/models/api.py,sha256=KlVUbApyz6uuWefAN9K4B_vWDSps5hLW6hNg1Eo3TBQ,6996
+ws_bom_robot_app/llm/models/api.py,sha256=14CPG9hCu2rDMNrUGpvi9SOfKr-ALSBZfKtliSjnwEs,6570
 ws_bom_robot_app/llm/models/base.py,sha256=1TqxuTK3rjJEALn7lvgoen_1ba3R2brAgGx6EDTtDZo,152
 ws_bom_robot_app/llm/models/kb.py,sha256=9zqwDlVULVrWE48wo5AivzWoOtnjA57k9rsw8KNnyDk,8935
 ws_bom_robot_app/llm/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -49,10 +49,10 @@ ws_bom_robot_app/llm/vector_store/integration/sharepoint.py,sha256=zqqn-6qPrK50P
 ws_bom_robot_app/llm/vector_store/integration/sitemap.py,sha256=nPbIywp-ZwWbWStvjvYVgHqqejyYFr8eZhBc8ycTuaU,4206
 ws_bom_robot_app/llm/vector_store/integration/slack.py,sha256=FMjESXm2QetFXI6i8epze7Kbbu22fV8CVaxb71AHnJ8,2572
 ws_bom_robot_app/llm/vector_store/loader/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ws_bom_robot_app/llm/vector_store/loader/base.py,sha256=tzUBO5FU552iRDhCqFUveBo3GjWhuqL5nCtSL8AJhGk,5022
-ws_bom_robot_app/llm/vector_store/loader/docling.py,sha256=dns_A--Wb-oIGYcbrW5RQ6-ALR5cCmySioo389K0GK0,1775
+ws_bom_robot_app/llm/vector_store/loader/base.py,sha256=ugc1Vhn_PJKD4NnL1QLQg98TzxBb-dPBEFqzR2PEIvI,5164
+ws_bom_robot_app/llm/vector_store/loader/docling.py,sha256=LEYwABQ5dHvFVLgjZ35yHJmk8r9cnOsl-9UnWp_LBpU,2080
 ws_bom_robot_app/llm/vector_store/loader/json_loader.py,sha256=qo9ejRZyKv_k6jnGgXnu1W5uqsMMtgqK_uvPpZQ0p74,833
-ws_bom_robot_app-0.0.27.dist-info/METADATA,sha256=YkrE-lnXbTolfCZ7cmJs2F8ugQzbc-g7WDF-ylaIL6s,7529
-ws_bom_robot_app-0.0.27.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-ws_bom_robot_app-0.0.27.dist-info/top_level.txt,sha256=Yl0akyHVbynsBX_N7wx3H3ZTkcMLjYyLJs5zBMDAKcM,17
-ws_bom_robot_app-0.0.27.dist-info/RECORD,,
+ws_bom_robot_app-0.0.29.dist-info/METADATA,sha256=y64ajFk7rJsIh5GDGMKnfJ8vVrDij1IMNJEeT8PX3bk,7853
+ws_bom_robot_app-0.0.29.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+ws_bom_robot_app-0.0.29.dist-info/top_level.txt,sha256=Yl0akyHVbynsBX_N7wx3H3ZTkcMLjYyLJs5zBMDAKcM,17
+ws_bom_robot_app-0.0.29.dist-info/RECORD,,

{ws_bom_robot_app-0.0.27.dist-info → ws_bom_robot_app-0.0.29.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.6.0)
+Generator: setuptools (75.8.0)
 Root-Is-Purelib: true
 Tag: py3-none-any