class TestObj(BaseModel):
id: str = Field(description="Unique identifier.")
def test_fn(obj: TestObj):
return 1
FunctionTool.from_defaults(test_fn),RuntimeError: no validator found for <class 'app.leader_agent.TestObj'>, see arbitrary_types_allowed in ConfigIngestionPipeline run that's from a StorageContext? the vector_store param on IP takes a BasePydanticVector store a storage_context.vector_store is my SimpleVectorStore. it's throwing a dict invalid errorIngestionPipeline(
transformations=[...],
docstore=storage_context.docstore, # loads/uses sc docstore
# errors: vector_store=storage_context.vector_store
).run(documents=documents)docstore after getting the document nodes, since there's no storage_context arg to SimpleDirectoryReader)vector_store here but should i also update the docstore? will vector_stores[vector_store.name] automatically add the chunks/nodes from transformation? will it only do that if one of the transformation steps adds embeddings to each node?add_index_struct and read it later by rebuilding an index from an index struct?)class CustomExtractor(BaseExtractor):
def extract(self, nodes):
metadata_list = [
{
"custom": (
node.metadata["document_title"]
+ "\n"
+ node.metadata["excerpt_keywords"]
)
}
for node in nodes
]
return metadata_listTypeError: Can't instantiate abstract class CustomExtractor with abstract method aextract when pasting the documentation code as isStorageContext.from_defaults(persist_dir) i get a FileNotFoundError: [Errno 2] No such file or .../docstore.json. shouldn't that be created if it doesn't exist (first time) and otherwise loaded in?stop_sequence to Anthropic LLM? TypeError: Messages.create() got an unexpected keyword argument 'stop_sequence'system_prompt kwargllm = Anthropic( system_prompt=system_prompt
self.memory.put(ChatMessage(content=system_prompt, role=MessageRole.SYSTEM))
TypeError: Messages.create() got an unexpected keyword argument 'tools'. is there any guidance on tool calling with llama's anthropic wrapper?chat_repl). has anyone else bumped into that?