pg_vector_store = PGVectorStore.from_params(
**POSTGRES_SETTINGS.model_dump(exclude_none=True),
table_name="embeddings",
embed_dim=384,
)
pipeline = IngestionPipeline(
transformations=[
HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5"),
],
docstore=postgres_docstore,
vector_store=pg_vector_store,
)validation_error = ValidationError(model='IngestionPipeline', errors=[{'loc': ('vector_store',), 'msg': "Can't instantiate abstract class...VectorStore without an implementation for abstract methods 'add', 'client', 'delete', 'query'", 'type': 'type_error'}])
def __init__(__pydantic_self__, **data: Any) -> None:
"""
Create a new model by parsing and validating input data from keyword arguments.
Raises ValidationError if the input data cannot be parsed to form a valid model.
"""
# Uses something other than `self` the first arg to allow "self" as a settable attribute
values, fields_set, validation_error = validate_model(__pydantic_self__.__class__, data)
if validation_error:
> raise validation_error
E pydantic.v1.error_wrappers.ValidationError: 1 validation error for IngestionPipeline
E vector_store
E Can't instantiate abstract class BasePydanticVectorStore without an implementation for abstract methods 'add', 'client', 'delete', 'query' (type=type_error) trace_map in end_trace to be None? In attempting to add arize-phoenix to privateGPT I'm noticing significantly different behavior than the toy project i created to test phoenix. For some reason the traces never get emmited in privateGPT and it seems to be because OpenInferenceTraceCallbackHandler.end_trace() is not called with trace_map. end_trace is called from as wellquery_stream = chat_service.stream_chat(
messages=all_messages,
use_context=True,
)chat_service.stream_chat() is of type CompletionGen which only contains a list of the sources. I'd like to keep around a copy of the whole prompt that is sent to the llm for each invocation of stream_chat for debugging purposes.ChatResponse from llama_index.core.llms and extend it with a custom pydantic model. MyModels to ChatResponse via subclassing like sofrom pydantic import BaseModel from llama_index.core.llms import ChatResponse class MyModel(BaseModel): foo: str class CompletionWithAttributions(ChatResponse): attributions: list[MyModel] | None = None
ChatResponse like sofrom pydantic import BaseModel class MyModel(BaseModel): foo: str class CompletionWithAttributions(BaseModel): attributions: list[MyModel] | None = None
BaseModel from llama-index itself like this, but that seems VERY clugy as elsewhere in my app i am importing BaseModel from pydantic as per usual.from llama_index.core.bridge.pydantic import BaseModel
doc = docstore.get_document(llama_id)
assert doc != None
doc_content = doc.get_content()
assert doc_content != Nonedocstore_ref_doc_info = docstore.get_all_ref_doc_info()
NotImplementedError: Vector store integrations that store text in the vector store are not supported by ref_doc_info yet.
llama_index package? It seems to be able to import stuff from llama_cloud like TextNode, but it has absolutely no idea what is exported from the llama_index package. Thanks so much for the help, I've spent a rediculous 3 hours on this issue today 🤦♂️from llama_index.core.bridge.pydantic import (
BaseModel
)llama_index.core.vector_storesclass ChatBody(BaseModel):
messages: list[OpenAIMessage]
use_context: bool = False
conversation_id: str | None = None
context_filter: MetadataFilters | None = None
include_sources: bool = True
stream: bool = Falsellama_index.core.bridge.pydantic which is a v1 modelLangChainLLM() is fundamentally different than other llms like LlamaCPP() or SagemakerLLM(), specifically in that you cannot set messages_to_prompt or completion_to_prompt on LangChainLLM but you can on the others. LangChainLLM is the only one that extends LLM instead of CustomLLM. hf = HuggingFaceTextGenInference(
inference_server_url="https://api-inference.huggingface.co/models/HuggingFaceH4/zephyr-7b-beta",
max_new_tokens=512,
top_k=10,
top_p=0.95,
typical_p=0.95,
temperature=0.01,
repetition_penalty=1.03,
)
prompt_style = get_prompt_style(settings.huggingface.prompt_style)
self.llm = LangChainLLM(llm=hf)messages_to_prompt function. Is there a way to do this?