pieter/eveAI
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

- Adding a Tenant Type

Browse Source 
- 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
This commit is contained in:
Josako
2024-09-13 15:43:40 +02:00
parent 9e14824249
commit 6cf660e622
41 changed files with 687 additions and 579 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
common/utils/model_utils.py
View File

@@ -147,10 +147,10 @@ def select_model_variables(tenant):
match llm_model:
case 'gpt-4o' | 'gpt-4o-mini':
tool_calling_supported = True
PDF_chunk_size = 10000
PDF_chunk_overlap = 200
PDF_min_chunk_size = 8000
PDF_max_chunk_size = 12000
processing_chunk_size = 10000
processing_chunk_overlap = 200
processing_min_chunk_size = 8000
processing_max_chunk_size = 12000
case _:
raise Exception(f'Error setting model variables for tenant {tenant.id} '
f'error: Invalid chat model')
@@ -165,18 +165,18 @@ def select_model_variables(tenant):
model=llm_model_ext,
temperature=model_variables['RAG_temperature'])
tool_calling_supported = True
PDF_chunk_size = 10000
PDF_chunk_overlap = 200
PDF_min_chunk_size = 8000
PDF_max_chunk_size = 12000
processing_chunk_size = 10000
processing_chunk_overlap = 200
processing_min_chunk_size = 8000
processing_max_chunk_size = 12000
case _:
raise Exception(f'Error setting model variables for tenant {tenant.id} '
f'error: Invalid chat provider')
model_variables['PDF_chunk_size'] = PDF_chunk_size
model_variables['PDF_chunk_overlap'] = PDF_chunk_overlap
model_variables['PDF_min_chunk_size'] = PDF_min_chunk_size
model_variables['PDF_max_chunk_size'] = PDF_max_chunk_size
model_variables['processing_chunk_size'] = processing_chunk_size
model_variables['processing_chunk_overlap'] = processing_chunk_overlap
model_variables['processing_min_chunk_size'] = processing_min_chunk_size
model_variables['processing_max_chunk_size'] = processing_max_chunk_size
if tool_calling_supported:
model_variables['cited_answer_cls'] = CitedAnswer