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
Specify `litellm` version in `requirements.txt`.
shaoyijiaea39855d36ed
diff --git a/knowledge_storm/lm.py b/knowledge_storm/lm.pyindex bc2b443..d5836f7 100644--- a/knowledge_storm/lm.py+++ b/knowledge_storm/lm.py@@ -37,7 +37,7 @@ with warnings.catch_warnings():litellm.drop_params = Truelitellm.telemetry = False-from litellm.caching import Cache+from litellm.caching.caching import Cachedisk_cache_dir = os.path.join(Path.home(), ".storm_local_cache")litellm.cache = Cache(disk_cache_dir=disk_cache_dir, type="disk")diff --git a/requirements.txt b/requirements.txtindex c6c10f6..14e68cf 100644--- a/requirements.txt+++ b/requirements.txt@@ -8,3 +8,5 @@ langchain-huggingfaceqdrant-clientlangchain-qdrantnumpy==1.26.4+litellm==1.59.3+diskcache\ No newline at end of file