ws-bom-robot-app 0.0.21__tar.gz → 0.0.23__tar.gz

{ws_bom_robot_app-0.0.21 → ws_bom_robot_app-0.0.23}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ws_bom_robot_app
-Version: 0.0.21
+Version: 0.0.23
 Summary: A FastAPI application serving ws bom/robot/llm platform ai.
 Home-page: https://github.com/websolutespa/bom
 Author: Websolute Spa
@@ -23,12 +23,19 @@ Requires-Dist: langchain-core==0.3.21
 Requires-Dist: faiss-cpu==1.9.0
 Requires-Dist: python-magic==0.4.27
 Requires-Dist: opencv-python-headless==4.10.0.84
-Requires-Dist: unstructured[all-docs]==0.15.14
+Requires-Dist: unstructured[all-docs]==0.16.11
 Requires-Dist: langchain_unstructured==0.1.5
 Requires-Dist: unstructured-ingest==0.3.8
+Requires-Dist: unstructured-ingest[azure]
 Requires-Dist: unstructured-ingest[confluence]
+Requires-Dist: unstructured-ingest[dropbox]
+Requires-Dist: unstructured-ingest[gcs]
+Requires-Dist: unstructured-ingest[google_drive]
 Requires-Dist: unstructured-ingest[github]
 Requires-Dist: unstructured-ingest[jira]
+Requires-Dist: unstructured-ingest[s3]
+Requires-Dist: unstructured-ingest[slack]
+Requires-Dist: unstructured-ingest[sftp]
 Requires-Dist: html5lib==1.1
 Requires-Dist: markdownify==0.14.1
 Requires-Dist: nebuly==0.3.33
@@ -207,6 +214,13 @@ launch debugger
 streamlit run debugger.py --server.port 6002
 ```
 
+dockerize app from src
+
+```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" -p 6001:6001 ws-bom-robot-app:src
+```
+
 ### ✈️ publish
 
 - [testpypi](https://test.pypi.org/project/ws-bom-robot-app/)

{ws_bom_robot_app-0.0.21 → ws_bom_robot_app-0.0.23}/README.md

@@ -172,6 +172,13 @@ launch debugger
 streamlit run debugger.py --server.port 6002
 ```
 
+dockerize app from src
+
+```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" -p 6001:6001 ws-bom-robot-app:src
+```
+
 ### ✈️ publish
 
 - [testpypi](https://test.pypi.org/project/ws-bom-robot-app/)

{ws_bom_robot_app-0.0.21 → ws_bom_robot_app-0.0.23}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name="ws_bom_robot_app",
-    version="0.0.21",
+    version="0.0.23",
     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-0.0.23/ws_bom_robot_app/llm/vector_store/integration/azure.py

@@ -0,0 +1,62 @@
+import asyncio
+from ws_bom_robot_app.llm.vector_store.integration.base import IntegrationStrategy, UnstructuredIngest
+from unstructured_ingest.v2.processes.connectors.fsspec.azure import AzureConnectionConfig, AzureAccessConfig, AzureDownloaderConfig, AzureIndexerConfig
+from langchain_core.documents import Document
+from ws_bom_robot_app.llm.vector_store.loader.base import Loader
+from typing import Union, Optional
+from pydantic import BaseModel, Field, AliasChoices
+class AzureParams(BaseModel):
+  """
+  AzureParams is a model that holds configuration parameters for connecting to Azure services.
+
+  Attributes:
+    remote_url (str): The URL of the remote Azure service, in the form az://<container> or az://<container>/<path> for sub-folders.
+    account_name (str): The name of the Azure storage account.
+    \nProvide one of the following:
+      - account_key (Optional[str]): The key for the Azure storage account. Default is None.
+      - connection_string (Optional[str]): The connection string for the Azure storage account. Default is None.
+      - sas_token (Optional[str]): The Shared Access Signature token for the Azure storage account. Default is None. Detail: https://learn.microsoft.com/en-us/azure/ai-services/translator/document-translation/how-to-guides/create-sas-tokens?tabs=Containers
+    recursive (bool): Indicates whether the operation should be recursive. Default is False.
+    extension (list[str]): A list of file extensions to filter the files. Default is None.
+  """
+  remote_url: str = Field(validation_alias=AliasChoices("remoteUrl","remote_url"))
+  account_name: str = Field(validation_alias=AliasChoices("accountName","account_name"))
+  account_key: Optional[str] = Field(default=None,validation_alias=AliasChoices("accountKey","account_key"))
+  connection_string: Optional[str]  = Field(default=None,validation_alias=AliasChoices("connectionString","connection_string"))
+  sas_token: Optional[str]  = Field(default=None,validation_alias=AliasChoices("sasToken","sas_token"))
+  recursive: bool = False
+  extension: list[str] = Field(default=None)
+class Azure(IntegrationStrategy):
+  def __init__(self, knowledgebase_path: str, data: dict[str, Union[str,int,list]]):
+    super().__init__(knowledgebase_path, data)
+    self.__data = AzureParams.model_validate(self.data)
+    self.__unstructured_ingest = UnstructuredIngest(self.working_directory)
+  def working_subdirectory(self) -> str:
+    return 'azure'
+  def run(self) -> None:
+    indexer_config = AzureIndexerConfig(
+      remote_url=self.__data.remote_url,
+      recursive=self.__data.recursive,
+      #sample_n_files=1
+    )
+    downloader_config = AzureDownloaderConfig(
+      download_dir=self.working_directory
+    )
+    connection_config = AzureConnectionConfig(
+      access_config=AzureAccessConfig(
+        account_name=self.__data.account_name,
+        account_key=self.__data.account_key,
+        connection_string=self.__data.connection_string,
+        sas_token=self.__data.sas_token
+        )
+    )
+    self.__unstructured_ingest.pipeline(
+      indexer_config,
+      downloader_config,
+      connection_config,
+      extension=self.__data.extension).run()
+  async def load(self) -> list[Document]:
+      await asyncio.to_thread(self.run)
+      await asyncio.sleep(1)
+      return await Loader(self.working_directory).load()
+

ws_bom_robot_app-0.0.23/ws_bom_robot_app/llm/vector_store/integration/base.py

@@ -0,0 +1,43 @@
+import os
+from langchain_core.documents import Document
+from abc import ABC, abstractmethod
+from unstructured_ingest.v2.interfaces import ProcessorConfig
+from unstructured_ingest.v2.pipeline.pipeline import Pipeline, PartitionerConfig, FiltererConfig
+from typing import Union
+
+class IntegrationStrategy(ABC):
+  def __init__(self, knowledgebase_path: str, data: dict[str, Union[str,int,list]]):
+    self.knowledgebase_path = knowledgebase_path
+    self.data = data
+    self.working_directory = os.path.join(self.knowledgebase_path,self.working_subdirectory())
+    os.makedirs(self.working_directory, exist_ok=True)
+  @property
+  @abstractmethod
+  def working_subdirectory(self) -> str:
+    pass
+  @abstractmethod
+  #@timer
+  def load(self) -> list[Document]:
+    pass
+
+class UnstructuredIngest():
+  def __init__(self, working_directory: str):
+    self.working_directory = working_directory
+  def pipeline(self,indexer,downloader,connection,extension: list[str] = None) -> Pipeline:
+    return Pipeline.from_configs(
+      context=ProcessorConfig(
+        reprocess=False,
+        verbose=False,
+        tqdm=False,
+        num_processes=2,
+        preserve_downloads=True,
+        download_only=True,
+        raise_on_error=False
+      ),
+      indexer_config=indexer,
+      downloader_config=downloader,
+      source_connection_config=connection,
+      partitioner_config=PartitionerConfig(),
+      filterer_config=FiltererConfig(file_glob=[f"**/*{ext}" for ext in extension] if extension else None)
+    )
+

ws_bom_robot_app-0.0.23/ws_bom_robot_app/llm/vector_store/integration/confluence.py

@@ -0,0 +1,53 @@
+import asyncio
+from ws_bom_robot_app.llm.vector_store.integration.base import IntegrationStrategy, UnstructuredIngest
+from unstructured_ingest.v2.processes.connectors.confluence import ConfluenceIndexerConfig, ConfluenceDownloaderConfig, ConfluenceConnectionConfig, ConfluenceAccessConfig
+from langchain_core.documents import Document
+from ws_bom_robot_app.llm.vector_store.loader.base import Loader
+from typing import Union
+from pydantic import BaseModel, Field, AliasChoices
+
+class ConfluenceParams(BaseModel):
+  """
+  ConfluenceParams is a data model for storing Confluence integration parameters.
+
+  Attributes:
+    url (str): The URL of the Confluence instance, e.g., 'https://example.atlassian.net'.
+    access_token (str): The access token for authenticating with Confluence, e.g., 'AT....'
+    user_email (str): The email address of the Confluence user
+    spaces (list[str]): A list of Confluence spaces to interact with, e.g., ['SPACE1', 'SPACE2'].
+    extension (list[str], optional): A list of file extensions to filter by. Defaults to None, e.g., ['.pdf', '.docx'].
+  """
+  url: str
+  access_token: str = Field(validation_alias=AliasChoices("accessToken","access_token"))
+  user_email: str = Field(validation_alias=AliasChoices("userEmail","user_email"))
+  spaces: list[str] = []
+  extension: list[str] = Field(default=None)
+class Confluence(IntegrationStrategy):
+  def __init__(self, knowledgebase_path: str, data: dict[str, Union[str,int,list]]):
+    super().__init__(knowledgebase_path, data)
+    self.__data = ConfluenceParams.model_validate(self.data)
+    self.__unstructured_ingest = UnstructuredIngest(self.working_directory)
+  def working_subdirectory(self) -> str:
+    return 'confluence'
+  def run(self) -> None:
+    indexer_config = ConfluenceIndexerConfig(
+      spaces=self.__data.spaces
+    )
+    downloader_config = ConfluenceDownloaderConfig(
+      download_dir=self.working_directory
+    )
+    connection_config = ConfluenceConnectionConfig(
+      access_config=ConfluenceAccessConfig(api_token=self.__data.access_token),
+      url=self.__data.url,
+      user_email=self.__data.user_email
+    )
+    self.__unstructured_ingest.pipeline(
+      indexer_config,
+      downloader_config,
+      connection_config,
+      extension=self.__data.extension).run()
+  async def load(self) -> list[Document]:
+      await asyncio.to_thread(self.run)
+      await asyncio.sleep(1)
+      return await Loader(self.working_directory).load()
+

ws_bom_robot_app-0.0.23/ws_bom_robot_app/llm/vector_store/integration/dropbox.py

@@ -0,0 +1,53 @@
+import asyncio
+from ws_bom_robot_app.llm.vector_store.integration.base import IntegrationStrategy, UnstructuredIngest
+from unstructured_ingest.v2.processes.connectors.fsspec.dropbox import DropboxConnectionConfig, DropboxAccessConfig, DropboxDownloaderConfig, DropboxIndexerConfig
+from langchain_core.documents import Document
+from ws_bom_robot_app.llm.vector_store.loader.base import Loader
+from typing import Union
+from pydantic import BaseModel, Field, AliasChoices
+class DropboxParams(BaseModel):
+  """
+  DropboxParams is a model for storing parameters required to interact with Dropbox.
+
+  Attributes:
+    remote_url (str): The URL of the remote Dropbox location, e.g. 'dropbox://demo-directory' or 'dropbox://demo-directory/sub-directory'.
+    token (str): The authentication token for accessing Dropbox.
+      create app: https://www.dropbox.com/developers, with file.content.read permission, and generate token.
+    recursive (bool, optional): A flag indicating whether to search directories recursively. Defaults to False.
+    extension (list[str], optional): A list of file extensions to filter by. Defaults to None, e.g. ['.pdf', '.docx'].
+  """
+  remote_url: str = Field(validation_alias=AliasChoices("remoteUrl","remote_url"))
+  token: str
+  recursive: bool = False
+  extension: list[str] = Field(default=None)
+class Dropbox(IntegrationStrategy):
+  def __init__(self, knowledgebase_path: str, data: dict[str, Union[str,int,list]]):
+    super().__init__(knowledgebase_path, data)
+    self.__data = DropboxParams.model_validate(self.data)
+    self.__unstructured_ingest = UnstructuredIngest(self.working_directory)
+  def working_subdirectory(self) -> str:
+    return 'dropbox'
+  def run(self) -> None:
+    indexer_config = DropboxIndexerConfig(
+      remote_url=self.__data.remote_url,
+      recursive=self.__data.recursive,
+      #sample_n_files=1
+    )
+    downloader_config = DropboxDownloaderConfig(
+      download_dir=self.working_directory
+    )
+    connection_config = DropboxConnectionConfig(
+      access_config=DropboxAccessConfig(
+        token=self.__data.token
+        )
+    )
+    self.__unstructured_ingest.pipeline(
+      indexer_config,
+      downloader_config,
+      connection_config,
+      extension=self.__data.extension).run()
+  async def load(self) -> list[Document]:
+      await asyncio.to_thread(self.run)
+      await asyncio.sleep(1)
+      return await Loader(self.working_directory).load()
+

ws_bom_robot_app-0.0.23/ws_bom_robot_app/llm/vector_store/integration/gcs.py

@@ -0,0 +1,62 @@
+import asyncio
+from ws_bom_robot_app.llm.vector_store.integration.base import IntegrationStrategy, UnstructuredIngest
+from unstructured_ingest.v2.processes.connectors.fsspec.gcs import GcsIndexerConfig, GcsConnectionConfig, GcsAccessConfig, GcsDownloaderConfig
+from langchain_core.documents import Document
+from ws_bom_robot_app.llm.vector_store.loader.base import Loader
+from typing import Union, Optional
+from pydantic import BaseModel, Field, AliasChoices
+class GcsParams(BaseModel):
+  """
+  GcsParams is a model that defines the parameters required for Google Cloud Storage (GCS) integration.
+  Documentation:
+    - create service account: https://cloud.google.com/iam/docs/service-accounts-create?hl=en#console
+    - create key: https://cloud.google.com/iam/docs/keys-create-delete?hl=en#creating
+    - export key in a single line\n
+    ```pwsh
+    (Get-Content -Path "<path-to-downloaded-key-file>" -Raw).Replace("`r`n", "").Replace("`n", "")
+    ```
+    - create bucket with 'Storage Object Viewer' permission: https://cloud.google.com/storage/docs/creating-buckets?hl=en#console
+    - add principal to bucket: https://cloud.google.com/storage/docs/access-control/using-iam-permissions?hl=en#console
+    - manage IAM policies: https://cloud.google.com/storage/docs/access-control/using-iam-permissions?hl=en
+
+  Attributes:
+    remote_url (str): The URL of the remote GCS bucket, e.g. 'gcs://demo-bucket' or 'gcs://demo-bucket/sub-directory'.
+    service_account_key (str): The service account key for accessing the GCS bucket.
+    recursive (bool): A flag indicating whether to recursively access the GCS bucket. Defaults to False.
+    extension (list[str]): A list of file extensions to filter the files in the GCS bucket. Defaults to None.
+  """
+  remote_url: str = Field(validation_alias=AliasChoices("remoteUrl","remote_url"))
+  service_account_key: str = Field(validation_alias=AliasChoices("serviceAccountKey","service_account_key"))
+  recursive: bool = False
+  extension: list[str] = Field(default=None)
+class Gcs(IntegrationStrategy):
+  def __init__(self, knowledgebase_path: str, data: dict[str, Union[str,int,list]]):
+    super().__init__(knowledgebase_path, data)
+    self.__data = GcsParams.model_validate(self.data)
+    self.__unstructured_ingest = UnstructuredIngest(self.working_directory)
+  def working_subdirectory(self) -> str:
+    return 'gcs'
+  def run(self) -> None:
+    indexer_config = GcsIndexerConfig(
+      remote_url=self.__data.remote_url,
+      recursive=self.__data.recursive,
+      #sample_n_files=1
+    )
+    downloader_config = GcsDownloaderConfig(
+      download_dir=self.working_directory
+    )
+    connection_config = GcsConnectionConfig(
+      access_config=GcsAccessConfig(
+        service_account_key=self.__data.service_account_key
+        )
+    )
+    self.__unstructured_ingest.pipeline(
+      indexer_config,
+      downloader_config,
+      connection_config,
+      extension=self.__data.extension).run()
+  async def load(self) -> list[Document]:
+      await asyncio.to_thread(self.run)
+      await asyncio.sleep(1)
+      return await Loader(self.working_directory).load()
+

{ws_bom_robot_app-0.0.21 → ws_bom_robot_app-0.0.23}/ws_bom_robot_app/llm/vector_store/integration/github.py

@@ -1,6 +1,7 @@
 import asyncio
 from typing import Optional, Union
-from ws_bom_robot_app.llm.vector_store.integration.base import IntegrationStrategy, UnstructuredIngest
+from ws_bom_robot_app.llm.vector_store.integration.base import IntegrationStrategy
+from unstructured_ingest.interfaces import  ProcessorConfig, ReadConfig
 from unstructured_ingest.connector.git import GitAccessConfig
 from unstructured_ingest.connector.github import SimpleGitHubConfig
 from unstructured_ingest.runner import GithubRunner
@@ -9,6 +10,15 @@ from ws_bom_robot_app.llm.vector_store.loader.base import Loader
 from pydantic import BaseModel, Field, AliasChoices
 
 class GithubParams(BaseModel):
+  """
+  GithubParams is a model for storing parameters required to interact with a GitHub repository.
+
+  Attributes:
+    repo (str): The name of the GitHub repository, e.g., 'companyname/reponame'
+    access_token (Optional[str]): The access token for authenticating with GitHub, e.g., 'ghp_1234567890'.
+    branch (Optional[str]): The branch of the repository to interact with. Defaults to 'main'.
+    file_ext (Optional[list[str]]): A list of file extensions to filter by, e.g. ['.md', '.pdf']. Defaults to an empty list.
+  """
   repo: str
   access_token: Optional[str] | None = Field(None,validation_alias=AliasChoices("accessToken","access_token"))
   branch: Optional[str] = 'main'
@@ -17,8 +27,6 @@ class Github(IntegrationStrategy):
   def __init__(self, knowledgebase_path: str, data: dict[str, Union[str,int,list]]):
     super().__init__(knowledgebase_path, data)
     self.__data = GithubParams.model_validate(self.data)
-    self.__loader = Loader(self.working_directory)
-    self.__unstructured_ingest = UnstructuredIngest(self.working_directory)
   def working_subdirectory(self) -> str:
     return 'github'
   def run(self) -> None:
@@ -35,12 +43,13 @@ class Github(IntegrationStrategy):
     )
     runner = GithubRunner(
       connector_config=config,
-      processor_config=self.__unstructured_ingest.processor_config(),
-      read_config=self.__unstructured_ingest.read_config(),
-      partition_config=self.__unstructured_ingest.partition_config(),
-      retry_strategy_config=self.__unstructured_ingest.retry_strategy_config()
+      processor_config=ProcessorConfig(reprocess=False,verbose=False,num_processes=2,raise_on_error=False),
+      read_config=ReadConfig(download_dir=self.working_directory,re_download=True,preserve_downloads=True,download_only=True),
+      partition_config=None,
+      retry_strategy_config=None
       )
     runner.run()
   async def load(self) -> list[Document]:
       await asyncio.to_thread(self.run)
-      return await self.__loader.load()
+      await asyncio.sleep(1)
+      return await Loader(self.working_directory).load()

ws_bom_robot_app-0.0.23/ws_bom_robot_app/llm/vector_store/integration/googledrive.py

@@ -0,0 +1,69 @@
+import asyncio
+from ws_bom_robot_app.llm.vector_store.integration.base import IntegrationStrategy, UnstructuredIngest
+from unstructured_ingest.v2.processes.connectors.google_drive import GoogleDriveConnectionConfig, GoogleDriveDownloaderConfig, GoogleDriveIndexerConfig, GoogleDriveAccessConfig
+from langchain_core.documents import Document
+from ws_bom_robot_app.llm.vector_store.loader.base import Loader
+from typing import Union
+from pydantic import BaseModel, Field, AliasChoices
+class GoogleDriveParams(BaseModel):
+  """
+  GoogleDriveParams is a model that holds parameters for Google Drive integration.
+
+  Attributes:
+    service_account_key (dict): The service account key for Google Drive API authentication \n
+      - detail: https://developers.google.com/workspace/guides/create-credentials#service-accountc \n
+      - create a service account key, download the JSON file, and pass the content of the JSON file as a dictionary \n
+      - e.g., {
+        "type": "service_account",
+        "project_id": "demo-project-123456",
+        "private_key_id": "**********",
+        "private_key": "-----BEGIN PRIVATE KEY-----...----END PRIVATE KEY-----",
+        "client_email": "demo-client@demo-project-123456.iam.gserviceaccount.com",
+        "client_id": "123456",
+        "auth_uri": "https://accounts.google.com/o/oauth2/auth",
+        "token_uri": "https://oauth2.googleapis.com/token",
+        "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
+        "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/demo-client%40demo-project-123456.iam.gserviceaccount.com",
+        "universe_domain": "googleapis.com"
+      }
+      - enable Google Drive API: https://console.cloud.google.com/marketplace/product/google/drive.googleapis.com
+      - copy email address of the service account and share the Google Drive with the email address: https://www.youtube.com/watch?v=ykJQzEe_2dM&t=2s
+
+    drive_id (str): The {folder_id} of the Google Drive to interact with, e.g., https://drive.google.com/drive/folders/{folder_id}
+    extensions (list[str]): A list of file extensions to filter the files in the Google Drive, e.g., ['.pdf', '.docx'].
+    recursive (bool): A flag indicating whether to search files recursively in the Google Drive.
+  """
+  service_account_key: dict = Field(validation_alias=AliasChoices("serviceAccountKey","service_account_key"))
+  drive_id: str = Field(validation_alias=AliasChoices("driveId","drive_id"))
+  extensions: list[str] = []
+  recursive: bool = False
+class GoogleDrive(IntegrationStrategy):
+  def __init__(self, knowledgebase_path: str, data: dict[str, Union[str,int,list]]):
+    super().__init__(knowledgebase_path, data)
+    self.__data = GoogleDriveParams.model_validate(self.data)
+    self.__unstructured_ingest = UnstructuredIngest(self.working_directory)
+  def working_subdirectory(self) -> str:
+    return 'googledrive'
+  def run(self) -> None:
+    indexer_config = GoogleDriveIndexerConfig(
+      extensions=self.__data.extensions,
+      recursive=self.__data.recursive
+    )
+    downloader_config = GoogleDriveDownloaderConfig(
+      download_dir=self.working_directory
+    )
+    connection_config = GoogleDriveConnectionConfig(
+      access_config=GoogleDriveAccessConfig(
+        service_account_key=self.__data.service_account_key
+        ),
+      drive_id=self.__data.drive_id
+    )
+    self.__unstructured_ingest.pipeline(
+      indexer_config,
+      downloader_config,
+      connection_config).run()
+  async def load(self) -> list[Document]:
+      await asyncio.to_thread(self.run)
+      await asyncio.sleep(1)
+      return await Loader(self.working_directory).load()
+

{ws_bom_robot_app-0.0.21 → ws_bom_robot_app-0.0.23}/ws_bom_robot_app/llm/vector_store/integration/jira.py

@@ -1,5 +1,6 @@
 import asyncio
-from ws_bom_robot_app.llm.vector_store.integration.base import IntegrationStrategy, UnstructuredIngest
+from ws_bom_robot_app.llm.vector_store.integration.base import IntegrationStrategy
+from unstructured_ingest.interfaces import  ProcessorConfig, ReadConfig
 from unstructured_ingest.connector.jira import SimpleJiraConfig, JiraAccessConfig
 from unstructured_ingest.runner import JiraRunner
 from langchain_core.documents import Document
@@ -8,6 +9,17 @@ from pydantic import BaseModel, Field, AliasChoices
 from typing import Optional, Union
 
 class JiraParams(BaseModel):
+  """
+  JiraParams is a Pydantic model that represents the parameters required to interact with a Jira instance.
+
+  Attributes:
+    url (str): The URL of the Jira instance, e.g., 'https://example.atlassian.net'.
+    access_token (str): The access token for authenticating with the Jira API.
+    user_email (str): The email address of the Jira user.
+    projects (list[str]): A list of project keys or IDs to interact with, e.g., ['SCRUM', 'PROJ1'].
+    boards (Optional[list[str]]): An optional list of board IDs to interact with. Defaults to None, e.g., ['1', '2'].
+    issues (Optional[list[str]]): An optional list of issue keys or IDs to interact with. Defaults to None, e.g., ['SCRUM-1', 'PROJ1-1'].
+  """
   url: str
   access_token: str = Field(validation_alias=AliasChoices("accessToken","access_token"))
   user_email: str = Field(validation_alias=AliasChoices("userEmail","user_email"))
@@ -18,8 +30,6 @@ class Jira(IntegrationStrategy):
   def __init__(self, knowledgebase_path: str, data: dict[str, Union[str,int,list]]):
     super().__init__(knowledgebase_path, data)
     self.__data = JiraParams.model_validate(self.data)
-    self.__loader = Loader(self.working_directory)
-    self.__unstructured_ingest = UnstructuredIngest(self.working_directory)
   def working_subdirectory(self) -> str:
     return 'jira'
   def run(self) -> None:
@@ -36,13 +46,13 @@ class Jira(IntegrationStrategy):
     )
     runner = JiraRunner(
       connector_config=config,
-      processor_config=self.__unstructured_ingest.processor_config(),
-      read_config=self.__unstructured_ingest.read_config(),
-      partition_config=self.__unstructured_ingest.partition_config(),
-      retry_strategy_config=self.__unstructured_ingest.retry_strategy_config()
+      processor_config=ProcessorConfig(reprocess=False,verbose=False,num_processes=2,raise_on_error=False),
+      read_config=ReadConfig(download_dir=self.working_directory,re_download=True,preserve_downloads=True,download_only=True),
+      partition_config=None,
+      retry_strategy_config=None
       )
     runner.run()
   async def load(self) -> list[Document]:
       await asyncio.to_thread(self.run)
       await asyncio.sleep(1)
-      return await self.__loader.load()
+      return await Loader(self.working_directory).load()

{ws_bom_robot_app-0.0.21 → ws_bom_robot_app-0.0.23}/ws_bom_robot_app/llm/vector_store/integration/manager.py

@@ -1,16 +1,31 @@
 from typing import Type
+from ws_bom_robot_app.llm.vector_store.integration.azure import Azure
 from ws_bom_robot_app.llm.vector_store.integration.base import IntegrationStrategy
 from ws_bom_robot_app.llm.vector_store.integration.confluence import Confluence
+from ws_bom_robot_app.llm.vector_store.integration.dropbox import Dropbox
+from ws_bom_robot_app.llm.vector_store.integration.gcs import Gcs
 from ws_bom_robot_app.llm.vector_store.integration.github import Github
+from ws_bom_robot_app.llm.vector_store.integration.googledrive import GoogleDrive
 from ws_bom_robot_app.llm.vector_store.integration.jira import Jira
+from ws_bom_robot_app.llm.vector_store.integration.s3 import S3
+from ws_bom_robot_app.llm.vector_store.integration.sftp import Sftp
 from ws_bom_robot_app.llm.vector_store.integration.sitemap import Sitemap
+from ws_bom_robot_app.llm.vector_store.integration.slack import Slack
 
 class IntegrationManager:
   _list: dict[str, Type[IntegrationStrategy]] = {
-    "llmkbsitemap": Sitemap,
+    "llmkbazure": Azure,
+    "llmkbconfluence": Confluence,
+    "llmkbdropbox": Dropbox,
     "llmkbgithub": Github,
+    "llmkbgcs": Gcs,
+    "llmkbgoogledrive": GoogleDrive,
     "llmkbjira": Jira,
-    "llmkbconfluence": Confluence,
+    "llmkbs3": S3,
+    "llmkbsftp": Sftp,
+    "llmkbsitemap": Sitemap,
+    "llmkbslack": Slack,
+
   }
   @classmethod
   def get_strategy(cls, name: str, knowledgebase_path: str, data: dict[str, str]) -> IntegrationStrategy:

ws_bom_robot_app-0.0.23/ws_bom_robot_app/llm/vector_store/integration/s3.py

@@ -0,0 +1,64 @@
+import asyncio
+from ws_bom_robot_app.llm.vector_store.integration.base import IntegrationStrategy, UnstructuredIngest
+from unstructured_ingest.v2.processes.connectors.fsspec.s3 import S3ConnectionConfig, S3AccessConfig, S3DownloaderConfig, S3IndexerConfig
+from langchain_core.documents import Document
+from ws_bom_robot_app.llm.vector_store.loader.base import Loader
+from typing import Union, Optional
+from pydantic import BaseModel, Field, AliasChoices
+class S3Params(BaseModel):
+  """
+  S3Params is a data model for storing parameters required to interact with an S3 bucket.
+  Documentation:
+    - ceate S3 bucket: https://docs.aws.amazon.com/AmazonS3/latest/userguide/GetStartedWithS3.html#creating-bucket
+    - enable authenticated bucket access: https://docs.aws.amazon.com/AmazonS3/latest/userguide/walkthrough1.html
+    - set policies s3:ListBucket and s3:GetObject: https://docs.aws.amazon.com/AmazonS3/latest/userguide/example-policies-s3.html
+    - generate key/secret: https://docs.aws.amazon.com/IAM/latest/UserGuide/id_credentials_access-keys.html#Using_CreateAccessKey
+    - optionally create STS token: https://docs.aws.amazon.com/IAM/latest/UserGuide/id_credentials_temp_request.html#api_getsessiontoken
+
+  Attributes:
+    remote_url (str): The URL of the remote S3 bucket, e.g., 's3://demo-bucket' or 's3://demo-bucket/sub-directory'.
+    key (Optional[str]): The AWS access key ID for the authenticated AWS IAM user, e.g., 'AKIAIOSFODNN7EXAMPLE'.
+    secret (Optional[str]): The corresponding AWS secret access key, e.g., 'wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY'.
+    token (Optional[str]):  If required, the AWS STS session token for temporary access. Default is None.
+    recursive (bool): A flag indicating whether to perform operations recursively. Default is False.
+    extension (list[str]): A list of file extensions to filter the files. Default is None. e.g., ['.pdf', '.docx'].
+  """
+  remote_url: str = Field(validation_alias=AliasChoices("remoteUrl","remote_url"))
+  key: str
+  secret: str
+  token: Optional[str]  = None
+  recursive: bool = False
+  extension: list[str] = Field(default=None)
+class S3(IntegrationStrategy):
+  def __init__(self, knowledgebase_path: str, data: dict[str, Union[str,int,list]]):
+    super().__init__(knowledgebase_path, data)
+    self.__data = S3Params.model_validate(self.data)
+    self.__unstructured_ingest = UnstructuredIngest(self.working_directory)
+  def working_subdirectory(self) -> str:
+    return 's3'
+  def run(self) -> None:
+    indexer_config = S3IndexerConfig(
+      remote_url=self.__data.remote_url,
+      recursive=self.__data.recursive,
+      #sample_n_files=1
+    )
+    downloader_config = S3DownloaderConfig(
+      download_dir=self.working_directory
+    )
+    connection_config = S3ConnectionConfig(
+      access_config=S3AccessConfig(
+        key=self.__data.key,
+        secret=self.__data.secret,
+        token=self.__data.token
+        )
+    )
+    self.__unstructured_ingest.pipeline(
+      indexer_config,
+      downloader_config,
+      connection_config,
+      extension=self.__data.extension).run()
+  async def load(self) -> list[Document]:
+      await asyncio.to_thread(self.run)
+      await asyncio.sleep(1)
+      return await Loader(self.working_directory).load()
+

ws_bom_robot_app-0.0.23/ws_bom_robot_app/llm/vector_store/integration/sftp.py

@@ -0,0 +1,64 @@
+import asyncio
+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 Union, Optional
+from pydantic import BaseModel, Field, AliasChoices
+class SftpParams(BaseModel):
+  """
+  SftpParams is a model that defines the parameters required for SFTP integration.
+
+  Attributes:
+    remote_url (str): The URL of the remote SFTP server, e.g. 'sftp://example.com' or 'sftp://example.com/directory'.
+    host (Optional[str]): The hostname or IP address of the SFTP server. Defaults to None and inferred from remote_url
+    port (Optional[int]): The port number to connect to on the SFTP server. Defaults to 22.
+    username (str): The username to authenticate with the SFTP server.
+    password (str): The password to authenticate with the SFTP server.
+    recursive (bool): Whether to perform recursive operations. Defaults to False.
+    extension (list[str]): A list of file extensions to filter by. Defaults to None, e.g. ['.pdf', '.docx'].
+  """
+  remote_url: str = Field(validation_alias=AliasChoices("remoteUrl","remote_url"))
+  host: Optional[str] = None
+  port: Optional[int] = 22
+  username: str
+  password: str
+  recursive: bool = False
+  extension: list[str] = Field(default=None)
+class Sftp(IntegrationStrategy):
+  def __init__(self, knowledgebase_path: str, data: dict[str, Union[str,int,list]]):
+    super().__init__(knowledgebase_path, data)
+    self.__data = SftpParams.model_validate(self.data)
+    self.__unstructured_ingest = UnstructuredIngest(self.working_directory)
+  def working_subdirectory(self) -> str:
+    return 'sftp'
+  def run(self) -> None:
+    indexer_config = SftpIndexerConfig(
+      remote_url=self.__data.remote_url,
+      recursive=self.__data.recursive,
+      #sample_n_files=1
+    )
+    downloader_config = SftpDownloaderConfig(
+      download_dir=self.working_directory,
+      remote_url=self.__data.remote_url
+    )
+    connection_config = SftpConnectionConfig(
+      access_config=SftpAccessConfig(
+        password=self.__data.password
+        ),
+      username=self.__data.username,
+      host=self.__data.host,
+      port=self.__data.port,
+      look_for_keys=False,
+      allow_agent=False
+    )
+    self.__unstructured_ingest.pipeline(
+      indexer_config,
+      downloader_config,
+      connection_config,
+      extension=self.__data.extension).run()
+  async def load(self) -> list[Document]:
+      await asyncio.to_thread(self.run)
+      await asyncio.sleep(1)
+      return await Loader(self.working_directory).load()
+

ws_bom_robot_app-0.0.23/ws_bom_robot_app/llm/vector_store/integration/slack.py

@@ -0,0 +1,57 @@
+import asyncio
+from ws_bom_robot_app.llm.vector_store.integration.base import IntegrationStrategy, UnstructuredIngest
+from unstructured_ingest.v2.processes.connectors.slack import SlackIndexerConfig, SlackDownloaderConfig, SlackConnectionConfig, SlackAccessConfig
+from langchain_core.documents import Document
+from ws_bom_robot_app.llm.vector_store.loader.base import Loader
+from typing import Union
+from pydantic import BaseModel, Field, AliasChoices
+from datetime import datetime, timedelta
+
+class SlackParams(BaseModel):
+  """
+  SlackParams is a data model for storing Slack integration parameters.
+  Documentation:
+    - create slack app: https://api.slack.com/quickstart#creating
+    - set channels:history scope: https://api.slack.com/quickstart#scopes
+    - installing app/get token: https://api.slack.com/quickstart#installing
+    - add app to channel/s
+
+  Attributes:
+    token (str): The authentication token for accessing the Slack API.
+    channels (list[str]): A list of Slack channel IDs, e.g. ['C01B2PZQX1V'].
+    num_days (int, optional): The number of days to retrieve messages from. Defaults to 7.
+    extension (list[str], optional): A list of file extensions to filter messages by, e.g. [".xml"]. Defaults to None.
+  """
+  token: str
+  channels: list[str]
+  num_days: int = Field(default=7,validation_alias=AliasChoices("numDays","num_days"))
+  extension: list[str] = Field(default=None)
+class Slack(IntegrationStrategy):
+  def __init__(self, knowledgebase_path: str, data: dict[str, Union[str,int,list]]):
+    super().__init__(knowledgebase_path, data)
+    self.__data = SlackParams.model_validate(self.data)
+    self.__unstructured_ingest = UnstructuredIngest(self.working_directory)
+  def working_subdirectory(self) -> str:
+    return 'slack'
+  def run(self) -> None:
+    indexer_config = SlackIndexerConfig(
+      channels=self.__data.channels,
+      start_date=datetime.now() - timedelta(days=self.__data.num_days),
+      end_date=datetime.now()
+    )
+    downloader_config = SlackDownloaderConfig(
+      download_dir=self.working_directory
+    )
+    connection_config = SlackConnectionConfig(
+      access_config=SlackAccessConfig(token=self.__data.token)
+    )
+    self.__unstructured_ingest.pipeline(
+      indexer_config,
+      downloader_config,
+      connection_config,
+      extension=self.__data.extension).run()
+  async def load(self) -> list[Document]:
+      await asyncio.to_thread(self.run)
+      await asyncio.sleep(1)
+      return await Loader(self.working_directory).load()
+

{ws_bom_robot_app-0.0.21 → ws_bom_robot_app-0.0.23}/ws_bom_robot_app/llm/vector_store/loader/base.py

@@ -1,15 +1,14 @@
 
-import asyncio
-from ws_bom_robot_app.config import config
-from typing import Any, Callable, Generator, Optional, Tuple
+import asyncio, gc, logging, os, traceback
+from typing import Any, Optional
 from langchain_community.document_loaders import DirectoryLoader
 from langchain_community.document_loaders.base import BaseLoader
 from langchain_community.document_loaders.merge import MergedDataLoader
 from langchain_core.documents import Document
 from langchain_unstructured import UnstructuredLoader
 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
-import gc, logging
 
 class LoaderConfig(BaseModel):
   loader: type[BaseLoader]
@@ -94,7 +93,7 @@ class Loader():
     for loader_config in loader_configs.values():
         loaders.append(
           DirectoryLoader(
-            self.knowledgebase_path,
+            os.path.abspath(self.knowledgebase_path),
             glob=loader_config["glob_patterns"],
             loader_cls=loader_config["loader_cls"],
             loader_kwargs=loader_config["loader_kwargs"],
@@ -110,17 +109,23 @@ class Loader():
   #@timer
   async def load(self) -> list[Document]:
     MAX_RETRIES = 3
-    loaders = MergedDataLoader(self.__directory_loader())
+    loaders: MergedDataLoader = MergedDataLoader(self.__directory_loader())
     try:
       for attempt in range(MAX_RETRIES):
         try:
-          return await loaders.aload()
-          #return await [doc async for doc in loaders.alazy_load()]
+          _documents = []
+          async for document in loaders.alazy_load():
+            _documents.append(document)
+          return _documents
         except Exception as e:
           logging.warning(f"Attempt {attempt+1} load document  failed: {e}")
           await asyncio.sleep(1)
           if attempt == MAX_RETRIES - 1:
-            logging.error(f"Failed to load documents: {e}")
+            tb = traceback.format_exc()
+            logging.error(f"Failed to load documents: {e} | {tb}")
             return []
+        finally:
+           del _documents
     finally:
+      del loaders
       gc.collect()

{ws_bom_robot_app-0.0.21 → ws_bom_robot_app-0.0.23}/ws_bom_robot_app/main.py

@@ -75,8 +75,14 @@ def diag(authenticate: bool = Depends(authenticate)):
     from ws_bom_robot_app.llm.vector_store.integration.manager import IntegrationManager as wsim
     from ws_bom_robot_app.llm.tools.tool_manager import ToolManager as wstm
     from ws_bom_robot_app.llm.agent_description import AgentDescriptor as wsad
+
     svmem = psutil.virtual_memory()
     swap = psutil.swap_memory()
+    try:
+      ws_bom_robot_app_version = pkg_resources.get_distribution("ws_bom_robot_app").version
+    except:
+      ws_bom_robot_app_version = "unknown"
+    peer_process_ids = [c.pid for c in psutil.Process(os.getppid()).children()] if config.runtime_options().is_multi_process else None
     return {
         "status":"ok",
         "uptime": {'from':_uptime,'elapsed':str(datetime.datetime.now()-_uptime)},
@@ -117,8 +123,9 @@ def diag(authenticate: bool = Depends(authenticate)):
             "os": {
                 "ppid": os.getppid(),
                 "pid": os.getpid(),
+                "pids": peer_process_ids,
                 "cwd": os.getcwd(),
-                "ws_bom_robot_app": pkg_resources.get_distribution("ws_bom_robot_app").version,
+                "ws_bom_robot_app": ws_bom_robot_app_version,
                 "env": os.environ,
             },
         },

{ws_bom_robot_app-0.0.21 → ws_bom_robot_app-0.0.23}/ws_bom_robot_app/requirements.txt

@@ -20,12 +20,19 @@ faiss-cpu==1.9.0
 #loaders
 python-magic==0.4.27
 opencv-python-headless==4.10.0.84 #docker specs
-unstructured[all-docs]==0.15.14
+unstructured[all-docs]==0.16.11
 langchain_unstructured==0.1.5
 unstructured-ingest==0.3.8
+unstructured-ingest[azure]
 unstructured-ingest[confluence]
+unstructured-ingest[dropbox]
+unstructured-ingest[gcs]
+unstructured-ingest[google_drive]
 unstructured-ingest[github]
 unstructured-ingest[jira]
+unstructured-ingest[s3]
+unstructured-ingest[slack]
+unstructured-ingest[sftp]
 html5lib==1.1 #beautifulsoup4 parser
 
 #integrations

{ws_bom_robot_app-0.0.21 → ws_bom_robot_app-0.0.23}/ws_bom_robot_app/task_manager.py

@@ -116,6 +116,7 @@ class TaskStatistics(BaseModel):
     class TaskStatisticExecutionInfo(BaseModel):
         retention_days: float = config.robot_task_retention_days
         max_concurrent: int
+        pid: int = os.getpid()
         running: list[TaskStatus]
         slowest: list
     class TaskStatisticExecutionTime(BaseModel):
@@ -169,7 +170,7 @@ class TaskManagerStrategy(ABC):
         pass
 
     def task_cleanup_rule(self, task: TaskEntry) -> bool:
-        return task.status.status in {"completed", "failure"} and datetime.fromisoformat(task.status.metadata.end_at) < datetime.now() - timedelta(days=config.robot_task_retention_days)
+        return task.status.metadata.start_at and datetime.fromisoformat(task.status.metadata.start_at) < datetime.now() - timedelta(days=config.robot_task_retention_days)
 
     def task_done_callback(self, task_entry: TaskEntry, headers: TaskHeader | None = None) -> Callable:
         def callback(task: asyncio.Task):

{ws_bom_robot_app-0.0.21 → ws_bom_robot_app-0.0.23}/ws_bom_robot_app.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ws_bom_robot_app
-Version: 0.0.21
+Version: 0.0.23
 Summary: A FastAPI application serving ws bom/robot/llm platform ai.
 Home-page: https://github.com/websolutespa/bom
 Author: Websolute Spa
@@ -23,12 +23,19 @@ Requires-Dist: langchain-core==0.3.21
 Requires-Dist: faiss-cpu==1.9.0
 Requires-Dist: python-magic==0.4.27
 Requires-Dist: opencv-python-headless==4.10.0.84
-Requires-Dist: unstructured[all-docs]==0.15.14
+Requires-Dist: unstructured[all-docs]==0.16.11
 Requires-Dist: langchain_unstructured==0.1.5
 Requires-Dist: unstructured-ingest==0.3.8
+Requires-Dist: unstructured-ingest[azure]
 Requires-Dist: unstructured-ingest[confluence]
+Requires-Dist: unstructured-ingest[dropbox]
+Requires-Dist: unstructured-ingest[gcs]
+Requires-Dist: unstructured-ingest[google_drive]
 Requires-Dist: unstructured-ingest[github]
 Requires-Dist: unstructured-ingest[jira]
+Requires-Dist: unstructured-ingest[s3]
+Requires-Dist: unstructured-ingest[slack]
+Requires-Dist: unstructured-ingest[sftp]
 Requires-Dist: html5lib==1.1
 Requires-Dist: markdownify==0.14.1
 Requires-Dist: nebuly==0.3.33
@@ -207,6 +214,13 @@ launch debugger
 streamlit run debugger.py --server.port 6002
 ```
 
+dockerize app from src
+
+```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" -p 6001:6001 ws-bom-robot-app:src
+```
+
 ### ✈️ publish
 
 - [testpypi](https://test.pypi.org/project/ws-bom-robot-app/)

{ws_bom_robot_app-0.0.21 → ws_bom_robot_app-0.0.23}/ws_bom_robot_app.egg-info/SOURCES.txt

@@ -42,12 +42,19 @@ ws_bom_robot_app/llm/utils/webhooks.py
 ws_bom_robot_app/llm/vector_store/__init__.py
 ws_bom_robot_app/llm/vector_store/generator.py
 ws_bom_robot_app/llm/vector_store/integration/__init__.py
+ws_bom_robot_app/llm/vector_store/integration/azure.py
 ws_bom_robot_app/llm/vector_store/integration/base.py
 ws_bom_robot_app/llm/vector_store/integration/confluence.py
+ws_bom_robot_app/llm/vector_store/integration/dropbox.py
+ws_bom_robot_app/llm/vector_store/integration/gcs.py
 ws_bom_robot_app/llm/vector_store/integration/github.py
+ws_bom_robot_app/llm/vector_store/integration/googledrive.py
 ws_bom_robot_app/llm/vector_store/integration/jira.py
 ws_bom_robot_app/llm/vector_store/integration/manager.py
+ws_bom_robot_app/llm/vector_store/integration/s3.py
+ws_bom_robot_app/llm/vector_store/integration/sftp.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/loader/__init__.py
 ws_bom_robot_app/llm/vector_store/loader/base.py
 ws_bom_robot_app/llm/vector_store/loader/json_loader.py

{ws_bom_robot_app-0.0.21 → ws_bom_robot_app-0.0.23}/ws_bom_robot_app.egg-info/requires.txt

@@ -11,12 +11,19 @@ langchain-core==0.3.21
 faiss-cpu==1.9.0
 python-magic==0.4.27
 opencv-python-headless==4.10.0.84
-unstructured[all-docs]==0.15.14
+unstructured[all-docs]==0.16.11
 langchain_unstructured==0.1.5
 unstructured-ingest==0.3.8
+unstructured-ingest[azure]
 unstructured-ingest[confluence]
+unstructured-ingest[dropbox]
+unstructured-ingest[gcs]
+unstructured-ingest[google_drive]
 unstructured-ingest[github]
 unstructured-ingest[jira]
+unstructured-ingest[s3]
+unstructured-ingest[slack]
+unstructured-ingest[sftp]
 html5lib==1.1
 markdownify==0.14.1
 nebuly==0.3.33

ws_bom_robot_app-0.0.21/ws_bom_robot_app/llm/vector_store/integration/base.py

@@ -1,44 +0,0 @@
-import os
-from langchain_core.documents import Document
-from abc import ABC, abstractmethod
-from unstructured_ingest.interfaces import PartitionConfig,  ProcessorConfig, ReadConfig, RetryStrategyConfig
-from typing import Union
-
-class IntegrationStrategy(ABC):
-  def __init__(self, knowledgebase_path: str, data: dict[str, Union[str,int,list]]):
-    self.knowledgebase_path = knowledgebase_path
-    self.data = data
-    self.working_directory = os.path.join(self.knowledgebase_path,self.working_subdirectory())
-    os.makedirs(self.working_directory, exist_ok=True)
-  @property
-  @abstractmethod
-  def working_subdirectory(self) -> str:
-    pass
-  @abstractmethod
-  #@timer
-  def load(self) -> list[Document]:
-    pass
-
-class UnstructuredIngest():
-  def __init__(self, working_directory: str):
-    self.working_directory = working_directory
-  def processor_config(self) -> ProcessorConfig:
-    return ProcessorConfig(
-      reprocess=False,
-      verbose=False,
-      work_dir=os.path.abspath(self.working_directory),
-      #output_dir=os.path.abspath(self.working_directory),
-      num_processes=1,
-      raise_on_error=False
-    )
-  def read_config(self) -> ReadConfig:
-    return ReadConfig(
-      download_dir=os.path.abspath(self.working_directory),
-      re_download=True,
-      preserve_downloads=True,
-      download_only=True
-    )
-  def partition_config(self) -> PartitionConfig:
-    return None
-  def retry_strategy_config(self) -> RetryStrategyConfig:
-    return None

ws_bom_robot_app-0.0.21/ws_bom_robot_app/llm/vector_store/integration/confluence.py

@@ -1,47 +0,0 @@
-import asyncio
-from ws_bom_robot_app.llm.vector_store.integration.base import IntegrationStrategy, UnstructuredIngest
-from unstructured_ingest.connector.confluence import SimpleConfluenceConfig, ConfluenceAccessConfig
-from unstructured_ingest.runner import ConfluenceRunner
-from langchain_core.documents import Document
-from ws_bom_robot_app.llm.vector_store.loader.base import Loader
-from typing import Optional, Union
-from pydantic import BaseModel, Field, AliasChoices
-
-class ConfluenceParams(BaseModel):
-  url: str
-  access_token: str = Field(validation_alias=AliasChoices("accessToken","access_token"))
-  user_email: str = Field(validation_alias=AliasChoices("userEmail","user_email"))
-  spaces: list[str] = []
-class Confluence(IntegrationStrategy):
-  def __init__(self, knowledgebase_path: str, data: dict[str, Union[str,int,list]]):
-    super().__init__(knowledgebase_path, data)
-    self.__data = ConfluenceParams.model_validate(self.data)
-    self.__loader = Loader(self.working_directory)
-    self.__unstructured_ingest = UnstructuredIngest(self.working_directory)
-  def working_subdirectory(self) -> str:
-    return 'confluence'
-  def run(self) -> None:
-    access_config = ConfluenceAccessConfig(
-      api_token=self.__data.access_token
-    )
-    config = SimpleConfluenceConfig(
-      user_email=self.__data.user_email,
-      url = self.__data.url,
-      access_config=access_config,
-      #max_num_of_spaces=self.data.get('max_num_of_spaces',500),
-      #max_num_of_docs_from_each_space=self.data.get('max_num_of_docs_from_each_space',100),
-      spaces=self.__data.spaces
-    )
-    runner = ConfluenceRunner(
-      connector_config=config,
-      processor_config=self.__unstructured_ingest.processor_config(),
-      read_config=self.__unstructured_ingest.read_config(),
-      partition_config=self.__unstructured_ingest.partition_config(),
-      retry_strategy_config=self.__unstructured_ingest.retry_strategy_config()
-      )
-    runner.run()
-  async def load(self) -> list[Document]:
-      await asyncio.to_thread(self.run)
-      await asyncio.sleep(1)
-      return await self.__loader.load()
-