- 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/pdf_processor.py

@@ -16,10 +16,10 @@ class PDFProcessor(Processor):
     def __init__(self, tenant, model_variables, document_version):
         super().__init__(tenant, model_variables, document_version)
         # PDF-specific initialization
-        self.chunk_size = model_variables['PDF_chunk_size']
-        self.chunk_overlap = model_variables['PDF_chunk_overlap']
-        self.min_chunk_size = model_variables['PDF_min_chunk_size']
-        self.max_chunk_size = model_variables['PDF_max_chunk_size']
+        self.chunk_size = model_variables['processing_chunk_size']
+        self.chunk_overlap = model_variables['processing_chunk_overlap']
+        self.min_chunk_size = model_variables['processing_min_chunk_size']
+        self.max_chunk_size = model_variables['processing_max_chunk_size']
 
     def process(self):
         self._log("Starting PDF processing")
@@ -228,12 +228,7 @@ class PDFProcessor(Processor):
         for chunk in chunks:
             input = {"pdf_content": chunk}
             result = chain.invoke(input)
-            # Remove Markdown code block delimiters if present
-            result = result.strip()
-            if result.startswith("```markdown"):
-                result = result[len("```markdown"):].strip()
-            if result.endswith("```"):
-                result = result[:-3].strip()
+            result = self._clean_markdown(result)
             markdown_chunks.append(result)
 
         return "\n\n".join(markdown_chunks)