sys:1: RuntimeWarning: coroutine 'BaseQueryEngine.aquery' was never awaitedrun_jobs function takes the coroutine though so things dont'need to be awaited...RuntimeError: asyncio.run() cannot be called from a running event loopdoc = Document(_id="some calculated unique id hash") and I am nott sure if the database will fail an integrity error if the _id is not unique for some doc_id and generated node as the node_id is a random id...SubQuestionQueryEngine but get outputs like the CitationQueryEngine? Or will these require a new custom class.[]def setup_storage_context():
from dotenv import load_dotenv
from sqlalchemy import make_url
from llama_index import StorageContext
from llama_index.vector_stores import PGVectorStore
from llama_index.storage.docstore import SimpleDocumentStore
from llama_index.storage.index_store import SimpleIndexStore
load_dotenv()
url = make_url(os.getenv("DATABASE_URL"))
storage_context = StorageContext.from_defaults(
docstore=SimpleDocumentStore(),
index_store=SimpleIndexStore(),
vector_store=PGVectorStore.from_params(
database="test",
host=url.host,
port=url.port,
user=url.username,
password=url.password,
embed_dim=768,
hybrid_search=True,
debug=True
)
)
return storage_context
storage_context = setup_storage_context()
indices = load_indices_from_storage(storage_context)
print(indices)index.storage_context.persist()docker run --gpus all -p 8000:8000 ghcr.io/mistralai/mistral-src/vllm:latest \
--host 0.0.0.0 \
--model mistralai/Mistral-7B-Instruct-v0.2 \
--tensor-parallel-size 1huggingface_hub.inference._text_generation.ValidationError: Input validation error: `inputs` tokens + `max_new_tokens` must be <= 4096. Given: 3896 `inputs` tokens and 256 `max_new_tokens` make: *** [evals] Error 1
resp = agent.stream_chat("My name is Jordan")
for part in resp.chat_stream:
print(part)