Find answers from the community

L
LORKA
Offline, last seen 2 months ago
Joined September 25, 2024
Can a ContextChatEngine be made using QueryPipelines?
2 comments
L
When trying to perform queries on multiple index i've seen there are different approaches. Should I be using a SubQuestionQueryEngine with and QueryEngineTool for every index or make an Composable Graph Index with all the Indices, or maybe both.
17 comments
L
L
L
LORKA
·

Retriever

When using the document summary index as query engine, does the retriever retrives the nodes of the documents or the summaries?
1 comment
L
Hi im having trouble deleting a file from an index while using the DocumentSummaryIndex.
7 comments
L
If I want to the retriever to take in account the date metadata and assign better score to new nodes to avoid retrieving outdated nodes. How should I approach?
4 comments
L
L
While using an ingestion pipeline that ingest in a qdrant vector store I'm having problems with the GPU VRAM. The vectors are store in the qdrant but the gpu memory does not flush until the python process is killed
4 comments
L
L
W
L
LORKA
·

```

Plain Text
chat_id = "test"
docstore = RedisDocumentStore.from_redis_client(
    redis_client=redis_client,
    namespace="Docstore",
)
index_store = RedisIndexStore.from_redis_client(
    redis_client=redis_client,
    namespace="IndexStore"
)
vector_store = RedisVectorStore(
    redis_url=f"redis://:{REDIS_DB_PASSWORD}@{REDIS_DB_HOST}:{REDIS_DB_PORT}/0",
    index_name="VectorStore" + chat_id,
    index_prefix=chat_id
)

storage_context=StorageContext.from_defaults(
    docstore=docstore, index_store=index_store, vector_store=vector_store
)

index = VectorStoreIndex(
    nodes=[],
    storage_context=storage_context,
    service_context=service_context)

print(index.as_chat_engine(ChatMode.CONTEXT).chat("hola"))


The code above fails. With the following error:

raise response
redis.exceptions.ResponseError: VectorStoretest: no such index
9 comments
b
L
L
Hello, when creating an VectorStoreIndex should use as arguments a VectorStore for the embeddings and an IndexStore to save the index?
2 comments
L
f
Why the RedisVectorStore adds a prefix to the vectors?
30 comments
L
L
W
Hi everyone, im trying to load my index from a RedisIndexStore but when i query i get an EmptyResponse.
43 comments
L
L
L
LORKA
·

Hi everyone.

Hi everyone.
Im trying to use llamaindex as a middle man between my llm and the user.
As I dont have any document i tought that using an EmpyIndex would be the aproppiate solution, but when i query it returns an empty index because the nodes retrived is an empty list, and by default if nodes =[] the return is Empty Response.
Does anyone have an idea of how it should be done?
1 comment
L