MCPcopy
hub / github.com/llmware-ai/llmware / Status

Class Status

llmware/resources.py:5175–5303  ·  view source on GitHub ↗

Provides callers with an interface on the status of the parsing and embedding process. ``Status`` is the central class for accessing (reading and writing) the status of processes. The intended use case is to be an interface for non-llmware components (the callers) that need informat

Source from the content-addressed store, hash-verified

5173
5174
5175class Status:
5176
5177 """Provides callers with an interface on the status of the parsing and embedding process.
5178
5179 ``Status`` is the central class for accessing (reading and writing) the status of processes.
5180 The intended use case is to be an interface for non-llmware components (the callers) that need
5181 information on llmware progress, e.g user interface components may need to change depending on the
5182 progress of parsing. A status consists of a summary string and metrics that can be used to provide
5183 graphical widgets an update. If a status is written to SQL collection database, then it will use the
5184 Status schema defined in configs.py.
5185
5186 Parameters
5187 ----------
5188 account_name : str, optional, default='llmware'
5189 Sets the name of the account, which is used for writting and retrieving a status.
5190
5191 Returns
5192 -------
5193 status : Status
5194 A new ``Status`` object.
5195
5196 """
5197
5198 def __init__(self, account_name="llmware"):
5199
5200 self.account_name = account_name
5201 self.schema = LLMWareTableSchema.get_status_schema()
5202
5203 # if table does not exist (and required by the underlying collection db), then create
5204 if CollectionWriter("status", account_name=self.account_name).check_if_table_build_required():
5205 # create "status" table
5206 CollectionWriter("status", account_name=self.account_name).create_table("status", self.schema)
5207
5208 def get_pdf_parsing_status(self, library_name, job_id="0"):
5209
5210 """ Gets the status written by the PDF parser """
5211
5212 status_key = f"{library_name}_pdf_parser_{job_id}"
5213 status = CollectionRetrieval("status", account_name=self.account_name).lookup("key", status_key)
5214
5215 return status
5216
5217 def get_office_parsing_status(self, library_name, job_id="0"):
5218
5219 """ Gets the status written by the Office parser """
5220
5221 status_key = f"{library_name}_office_parser_{job_id}"
5222 status = CollectionRetrieval("status", account_name=self.account_name).lookup("key", status_key)
5223
5224 return status
5225
5226 # Return the status dict
5227 def get_embedding_status(self, library_name, embedding_model):
5228
5229 """ Gets the embedding status written by the EmbeddingHandler class and each supported vector DB """
5230
5231 status_key = self._get_embedding_status_key(library_name, embedding_model)
5232 status = CollectionRetrieval("status", account_name=self.account_name).lookup("key", status_key)

Callers 15

create_new_embeddingMethod · 0.90
create_new_embeddingMethod · 0.90
create_new_embeddingMethod · 0.90
create_new_embeddingMethod · 0.90
create_new_embeddingMethod · 0.90
create_new_embeddingMethod · 0.90
create_new_embeddingMethod · 0.90
create_new_embeddingMethod · 0.90
create_new_embeddingMethod · 0.90
create_new_embeddingMethod · 0.90

Calls

no outgoing calls

Tested by 1