ws-bom-robot-app 0.0.16__py3-none-any.whl → 0.0.18__py3-none-any.whl

ws_bom_robot_app/llm/vector_store/integration/base.py

@@ -1,10 +1,11 @@
 import os
 from langchain_core.documents import Document
 from abc import ABC, abstractmethod
-from ws_bom_robot_app.util import timer
+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, str]):
+  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())
@@ -17,3 +18,27 @@ class IntegrationStrategy(ABC):
   #@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.join(self.working_directory,'.__work_dir'),
+      #output_dir=self.working_directory,
+      num_processes=1,
+      raise_on_error=False
+    )
+  def read_config(self) -> ReadConfig:
+    return ReadConfig(
+      download_dir=self.working_directory,
+      re_download=True,
+      preserve_downloads=False,
+      download_only=True
+    )
+  def partition_config(self) -> PartitionConfig:
+    return None
+  def retry_strategy_config(self) -> RetryStrategyConfig:
+    return None

ws_bom_robot_app/llm/vector_store/integration/confluence.py

@@ -0,0 +1,47 @@
+import asyncio
+import os
+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]:
+      self.run()
+      await asyncio.sleep(1)
+      return await self.__loader.load()

ws_bom_robot_app/llm/vector_store/integration/github.py

@@ -0,0 +1,48 @@
+import asyncio
+import os
+from typing import Optional, Union
+from ws_bom_robot_app.llm.vector_store.integration.base import IntegrationStrategy, UnstructuredIngest
+from unstructured_ingest.connector.git import GitAccessConfig
+from unstructured_ingest.connector.github import SimpleGitHubConfig
+from unstructured_ingest.runner import GithubRunner
+from langchain_core.documents import Document
+from ws_bom_robot_app.llm.vector_store.loader.base import Loader
+from pydantic import BaseModel, Field, AliasChoices
+
+class GithubParams(BaseModel):
+  repo: str
+  access_token: Optional[str] | None = Field(None,validation_alias=AliasChoices("accessToken","access_token"))
+  branch: Optional[str] = 'main'
+  file_ext: Optional[list[str]] = Field(default_factory=list, validation_alias=AliasChoices("fileExt","file_ext"))
+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:
+    access_config = GitAccessConfig(
+      access_token=self.__data.access_token
+    )
+    file_ext = self.__data.file_ext or None
+    file_glob = [f"**/*{ext}" for ext in file_ext] if file_ext else None
+    config = SimpleGitHubConfig(
+      url = self.__data.repo,
+      access_config=access_config,
+      branch=self.__data.branch,
+      file_glob=file_glob
+    )
+    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()
+      )
+    runner.run()
+  async def load(self) -> list[Document]:
+      self.run()
+      await asyncio.sleep(1)
+      return await self.__loader.load()

ws_bom_robot_app/llm/vector_store/integration/jira.py

@@ -0,0 +1,49 @@
+import asyncio
+import os
+from ws_bom_robot_app.llm.vector_store.integration.base import IntegrationStrategy, UnstructuredIngest
+from unstructured_ingest.connector.jira import SimpleJiraConfig, JiraAccessConfig
+from unstructured_ingest.runner import JiraRunner
+from langchain_core.documents import Document
+from ws_bom_robot_app.llm.vector_store.loader.base import Loader
+from pydantic import BaseModel, Field, AliasChoices
+from typing import Optional, Union
+
+class JiraParams(BaseModel):
+  url: str
+  access_token: str = Field(validation_alias=AliasChoices("accessToken","access_token"))
+  user_email: str = Field(validation_alias=AliasChoices("userEmail","user_email"))
+  projects: list[str]
+  boards: Optional[list[str]] | None = None
+  issues: Optional[list[str]] | None = None
+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:
+    access_config = JiraAccessConfig(
+      api_token=self.__data.access_token
+    )
+    config = SimpleJiraConfig(
+      user_email=self.__data.user_email,
+      url = self.__data.url,
+      access_config=access_config,
+      projects=self.__data.projects,
+      boards=self.__data.boards,
+      issues=self.__data.issues
+    )
+    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()
+      )
+    runner.run()
+  async def load(self) -> list[Document]:
+      self.run()
+      await asyncio.sleep(1)
+      return await self.__loader.load()

ws_bom_robot_app/llm/vector_store/integration/manager.py

@@ -1,10 +1,16 @@
 from typing import Type
 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.github import Github
+from ws_bom_robot_app.llm.vector_store.integration.jira import Jira
 from ws_bom_robot_app.llm.vector_store.integration.sitemap import Sitemap
 
 class IntegrationManager:
   _list: dict[str, Type[IntegrationStrategy]] = {
     "llmkbsitemap": Sitemap,
+    "llmkbgithub": Github,
+    "llmkbjira": Jira,
+    "llmkbconfluence": Confluence,
   }
   @classmethod
   def get_strategy(cls, name: str, knowledgebase_path: str, data: dict[str, str]) -> IntegrationStrategy:

{ws_bom_robot_app-0.0.16.dist-info → ws_bom_robot_app-0.0.18.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ws_bom_robot_app
-Version: 0.0.16
+Version: 0.0.18
 Summary: A FastAPI application serving ws bom/robot/llm platform ai.
 Home-page: https://github.com/websolutespa/bom
 Author: Websolute Spa
@@ -25,6 +25,10 @@ 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: langchain_unstructured==0.1.5
+Requires-Dist: unstructured-ingest==0.3.8
+Requires-Dist: unstructured-ingest[confluence]
+Requires-Dist: unstructured-ingest[github]
+Requires-Dist: unstructured-ingest[jira]
 Requires-Dist: html5lib==1.1
 Requires-Dist: markdownify==0.14.1
 Requires-Dist: nebuly==0.3.33

{ws_bom_robot_app-0.0.16.dist-info → ws_bom_robot_app-0.0.18.dist-info}/RECORD

@@ -33,13 +33,16 @@ ws_bom_robot_app/llm/utils/webhooks.py,sha256=LAAZqyN6VhV13wu4X-X85TwdDgAV2rNvIw
 ws_bom_robot_app/llm/vector_store/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ws_bom_robot_app/llm/vector_store/generator.py,sha256=SrxrZ87JmWW4PQ-zP8upJJfamWur49fvH2eoIjEVoCI,5771
 ws_bom_robot_app/llm/vector_store/integration/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ws_bom_robot_app/llm/vector_store/integration/base.py,sha256=eCKD3U0KPoVDMtKr2iZqauMFEKd9b2k6rqPG_YjDy0g,626
-ws_bom_robot_app/llm/vector_store/integration/manager.py,sha256=cSFlE2erMv3Uchy788mlCFdcvmyeoqdeIiGmJ9QbLhY,583
+ws_bom_robot_app/llm/vector_store/integration/base.py,sha256=AUCIUw-Bv_NUH6nElPnda2Ib3iikj8O0nBFDoOskjlI,1502
+ws_bom_robot_app/llm/vector_store/integration/confluence.py,sha256=YP9vrkDVLw8ezZH9R3hc2Enp-wk71Uye4B3DIFasCUs,2145
+ws_bom_robot_app/llm/vector_store/integration/github.py,sha256=CtZTyM7vS2g9QzxXBOJ4nSfq4IehPua4UqPU56DcGko,2153
+ws_bom_robot_app/llm/vector_store/integration/jira.py,sha256=TRA6pb63KfKGJJUJ2Si1xCSaDeo-ZegHRQiAcfD2tcs,2078
+ws_bom_robot_app/llm/vector_store/integration/manager.py,sha256=YDQOgwMQxdRrVXIG3b0D6fHd1vGwQmgbAwigtWeeHW0,894
 ws_bom_robot_app/llm/vector_store/integration/sitemap.py,sha256=nPbIywp-ZwWbWStvjvYVgHqqejyYFr8eZhBc8ycTuaU,4206
 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=dhZ7F4EJmuYa2TBMggWVpQe4_NmS2wi312lHnNm5Jm0,4571
 ws_bom_robot_app/llm/vector_store/loader/json_loader.py,sha256=qo9ejRZyKv_k6jnGgXnu1W5uqsMMtgqK_uvPpZQ0p74,833
-ws_bom_robot_app-0.0.16.dist-info/METADATA,sha256=nZX2UZefJOJ6oQKd6OVC6g7tOeKYPZ1ALCmTH2fSYLY,6443
-ws_bom_robot_app-0.0.16.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-ws_bom_robot_app-0.0.16.dist-info/top_level.txt,sha256=Yl0akyHVbynsBX_N7wx3H3ZTkcMLjYyLJs5zBMDAKcM,17
-ws_bom_robot_app-0.0.16.dist-info/RECORD,,
+ws_bom_robot_app-0.0.18.dist-info/METADATA,sha256=j5xC1xXWb21rKPOCSS2Td6GvyN46J_sai_xDNW8Eavg,6620
+ws_bom_robot_app-0.0.18.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+ws_bom_robot_app-0.0.18.dist-info/top_level.txt,sha256=Yl0akyHVbynsBX_N7wx3H3ZTkcMLjYyLJs5zBMDAKcM,17
+ws_bom_robot_app-0.0.18.dist-info/RECORD,,