seanpedrickcase/llm_topic_modelling at a10d3880ca9f5f163c8c471c278bcae82b336189

Ctrl+K

3 contributors

Refactored call_llama_cpp_model function to include model parameter in chatfuncs.py and updated import statements in llm_api_call.py to reflect this change.

a10d388 5 months ago

__init__.py

0 Bytes

First commit 5 months ago
auth.py

1.54 kB

Allowed for server port, queue size, and file size to be specified by environment variables 5 months ago
aws_functions.py

7.02 kB

First commit 5 months ago
chatfuncs.py

8.51 kB

Refactored call_llama_cpp_model function to include model parameter in chatfuncs.py and updated import statements in llm_api_call.py to reflect this change. 5 months ago
helper_functions.py

12.7 kB

Added support for using local models (specifically Gemma 2b) for topic extraction and summary. Generally improved output format safeguards. 5 months ago
llm_api_call.py

88 kB

Refactored call_llama_cpp_model function to include model parameter in chatfuncs.py and updated import statements in llm_api_call.py to reflect this change. 5 months ago
prompts.py

4.67 kB

Corrected prompt. Now runs Haiku correctly 5 months ago