- Adding a Tenant Type

- Allow filtering on Tenant Types & searching for parts of Tenant names
- Implement health checks
- Start Prometheus monitoring (needs to be finalized)
- Refine audio_processor and srt_processor to reduce duplicate code and support for larger files
- Introduce repopack to reason in LLMs about the code

eveai_workers/Processors/html_processor.py

@@ -14,6 +14,9 @@ class HTMLProcessor(Processor):
         self.html_end_tags = model_variables['html_end_tags']
         self.html_included_elements = model_variables['html_included_elements']
         self.html_excluded_elements = model_variables['html_excluded_elements']
+        self.chunk_size = model_variables['processing_chunk_size']  # Adjust this based on your LLM's optimal input size
+        self.chunk_overlap = model_variables[
+            'processing_chunk_overlap']  # Adjust for context preservation between chunks
 
     def process(self):
         self._log("Starting HTML processing")
@@ -70,7 +73,7 @@ class HTMLProcessor(Processor):
         chain = setup | parse_prompt | llm | output_parser
 
         soup = BeautifulSoup(html_content, 'lxml')
-        chunks = self._split_content(soup)
+        chunks = self._split_content(soup, self.chunk_size)
 
         markdown_chunks = []
         for chunk in chunks: