- 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/srt_processor.py

@@ -1,37 +1,19 @@
-import re
-from langchain_core.output_parsers import StrOutputParser
-from langchain_core.prompts import ChatPromptTemplate
-from langchain_core.runnables import RunnablePassthrough
 from common.extensions import minio_client
-from common.utils.model_utils import create_language_template
-from .processor import Processor
+from .transcription_processor import TranscriptionProcessor
+import re
 
 
-class SRTProcessor(Processor):
-    def __init__(self, tenant, model_variables, document_version):
-        super().__init__(tenant, model_variables, document_version)
-
-    def process(self):
-        self._log("Starting SRT processing")
-        try:
-            file_data = minio_client.download_document_file(
-                self.tenant.id,
-                self.document_version.doc_id,
-                self.document_version.language,
-                self.document_version.id,
-                self.document_version.file_name
-            )
-
-            srt_content = file_data.decode('utf-8')
-            cleaned_transcription = self._clean_srt(srt_content)
-            markdown, title = self._generate_markdown_from_transcription(cleaned_transcription)
-
-            self._save_markdown(markdown)
-            self._log("Finished processing SRT")
-            return markdown, title
-        except Exception as e:
-            self._log(f"Error processing SRT: {str(e)}", level='error')
-            raise
+class SRTProcessor(TranscriptionProcessor):
+    def _get_transcription(self):
+        file_data = minio_client.download_document_file(
+            self.tenant.id,
+            self.document_version.doc_id,
+            self.document_version.language,
+            self.document_version.id,
+            self.document_version.file_name
+        )
+        srt_content = file_data.decode('utf-8')
+        return self._clean_srt(srt_content)
 
     def _clean_srt(self, srt_content):
         # Remove timecodes and subtitle numbers
@@ -50,31 +32,3 @@ class SRTProcessor(Processor):
 
         return cleaned_text
 
-    def _generate_markdown_from_transcription(self, transcription):
-        self._log("Generating markdown from transcription")
-        llm = self.model_variables['llm']
-        template = self.model_variables['transcript_template']
-        language_template = create_language_template(template, self.document_version.language)
-        transcript_prompt = ChatPromptTemplate.from_template(language_template)
-        setup = RunnablePassthrough()
-        output_parser = StrOutputParser()
-
-        chain = setup | transcript_prompt | llm | output_parser
-
-        input_transcript = {'transcript': transcription}
-        markdown = chain.invoke(input_transcript)
-
-        # Extract title from the markdown
-        title = self._extract_title_from_markdown(markdown)
-
-        return markdown, title
-
-    def _extract_title_from_markdown(self, markdown):
-        # Simple extraction of the first header as the title
-        lines = markdown.split('\n')
-        for line in lines:
-            if line.startswith('# '):
-                return line[2:].strip()
-        return "Untitled SRT Transcription"
-
-