- Significantly changed the PDF Processor to use Mistral's OCR model

- ensure very long chunks get split into smaller chunks
- ensure TrackedMistralAIEmbedding is batched if needed to ensure correct execution
- upgraded some of the packages to a higher version

common/utils/model_utils.py

@@ -135,6 +135,11 @@ def get_crewai_llm(full_model_name='mistral.mistral-large-latest', temperature=0
     return llm
 
 
+def process_pdf():
+    full_model_name = 'mistral-ocr-latest'
+
+
+
 class ModelVariables:
     """Manages model-related variables and configurations"""