Find answers from the community

Updated 3 months ago

Hi guys, just a quick question here in #

Hi guys, just a quick question here in because im not sure if i should be raising this here.

I'm currently trying to insert embeddings and other data into qDrant as part of LlamaIndex's IngestionPipeline.
Plain Text
client = qdrant_client.QdrantClient(path=vector_store_path)
        client.create_collection(collection_name=VECTOR_COLLECTION_NAME,vectors_config=models.VectorParams(size=param_size,distance=models.Distance.COSINE))
        return client
# other code here...
transformations=[
                TitleExtractor(nodes=3,llm=llm,num_workers=1),
                QuestionsAnsweredExtractor(questions=3,llm=llm,num_workers=1),
                SummaryExtractor(summaries=["prev","self","next"],llm=llm,num_workers=1),
                KeywordExtractor(llm=llm,num_workers=1),
                SentenceSplitter(chunk_size=2048,chunk_overlap=512),
                # TokenTextSplitter(chunk_size=1024,chunk_overlap=256),
                HuggingFaceEmbedding(model_name=embed_model)
                ],
                vector_store=vector_store
            )
            nodes = pipeline.run(documents=docs,show_progress=True)


While everything works well, the qdrant vector store created has a .lock text file created containing
Plain Text
tmp lock file

and is not releasing the lock even after everything has finished running.(The same problem occurs in .py and .ipynb files)

Is there any way for me to get qDrant to release the lock after all the data has been inserted?

I'm unsure if this an issue with the IngestionPipeline or should i be raising this to qDrant instead?

Thanks!
L
1 comment
hmm I actually have no idea on this one
Add a reply
Sign up and join the conversation on Discord