An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
Python agentic-ragdeep-researchemnlp2024knowledge-curationlarge-language-modelsnaaclnlpreport-generationretrieval-augmented-generation
chore: Update Gemini models in STORM Wiki pipeline
amr255b6080c402
diff --git a/examples/run_storm_wiki_gemini.py b/examples/run_storm_wiki_gemini.pyindex f1f1d2e..5e9f9c8 100644--- a/examples/run_storm_wiki_gemini.py+++ b/examples/run_storm_wiki_gemini.py@@ -43,9 +43,9 @@ def main(args):# https://ai.google.dev/gemini-api/docs/get-started/tutorial?lang=python#list_modelsconv_simulator_lm = GoogleModel(model='models/gemini-1.5-flash', max_tokens=500, **gemini_kwargs)question_asker_lm = GoogleModel(model='models/gemini-1.5-flash', max_tokens=500, **gemini_kwargs)- outline_gen_lm = GoogleModel(model='models/gemini-1.5-pro', max_tokens=400, **gemini_kwargs)- article_gen_lm = GoogleModel(model='models/gemini-1.5-pro', max_tokens=700, **gemini_kwargs)- article_polish_lm = GoogleModel(model='models/gemini-1.5-pro', max_tokens=4000, **gemini_kwargs)+ outline_gen_lm = GoogleModel(model='models/gemini-1.5-pro-exp-0801', max_tokens=400, **gemini_kwargs)+ article_gen_lm = GoogleModel(model='models/gemini-1.5-pro-exp-0801', max_tokens=700, **gemini_kwargs)+ article_polish_lm = GoogleModel(model='models/gemini-1.5-pro-exp-0801', max_tokens=4000, **gemini_kwargs)lm_configs.set_conv_simulator_lm(conv_simulator_lm)lm_configs.set_question_asker_lm(question_asker_lm)