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
Merge ollama support (#81).
shaoyijiaeaf858962578
diff --git a/README.md b/README.mdindex ddd56fc..806c541 100644--- a/README.md+++ b/README.md@@ -99,7 +99,7 @@ runner = STORMWikiRunner(engine_args, lm_configs, rm)```Currently, our package support:-- `OpenAIModel`, `AzureOpenAIModel`, `ClaudeModel`, `VLLMClient`, `TGIClient`, `TogetherClient` as language model components+- `OpenAIModel`, `AzureOpenAIModel`, `ClaudeModel`, `VLLMClient`, `TGIClient`, `TogetherClient`, `OllamaClient` as language model components- `YouRM`, `BingSearch`, `VectorRM` as retrieval module components:star2: **PRs for integrating more language models into [knowledge_storm/lm.py](knowledge_storm/lm.py) and search engines/retrievers into [knowledge_storm/rm.py](knowledge_storm/rm.py) are highly appreciated!**diff --git a/knowledge_storm/lm.py b/knowledge_storm/lm.pyindex c3e1ce8..e1ec8e2 100644--- a/knowledge_storm/lm.py+++ b/knowledge_storm/lm.py@@ -312,6 +312,7 @@ class VLLMClient(dspy.HFClientVLLM):print("Failed to parse JSON response:", response.text)raise Exception("Received invalid JSON response from server")+class OllamaClient(dspy.OllamaLocal):"""A wrapper class for dspy.OllamaClient."""diff --git a/setup.py b/setup.pyindex 8eb5015..e4fa40c 100644--- a/setup.py+++ b/setup.py@@ -16,7 +16,7 @@ with open("requirements.txt", encoding="utf-8") as f:setup(name="knowledge-storm",- version="0.2.2",+ version="0.2.3",author="Yijia Shao, Yucheng Jiang",author_email="[email protected], [email protected]",description="STORM: A language model-powered knowledge curation engine.",