LlamaIndex
Log in

Find answers from the community

Home
Members
edk
e
edk
Offline, last seen 3 months ago
Joined September 25, 2024
eedk
·

Can you split or merge multiple indexes

Can you split or merge multiple indexes? I have multiple documents I want to query together and in isolation. How can I approach this problem?
2 comments
e
L
eedk
·

Agents

Can llama index be used to create agents or is it preferred to use langchain instead?
7 comments
L
e
eedk
·

404

I am using the code below. Does anyone know how to ignore incase the url is 404 or similar http error
Plain Text
from llama_index.readers import SimpleWebPageReader

loader = SimpleWebPageReader()
documents = loader.load_data(urls=urls)
4 comments
e
E
eedk
·

In VectorStoreIndex.from_documents, is

In VectorStoreIndex.from_documents, is it possible to parse documents faster. The "parsing documents into nodes" step is taking sometime - hopefully it can be done in parallel if possible
1 comment
L
eedk
·

Indexing/Embedding question. How can I

Indexing/Embedding question. How can I speed up the embedding/indexing process of llama index. I have possibly thousands of documents I want to index as fast as possible. Any help is appreciated.
6 comments
L
e
T
eedk
·

Async

Hello. Does anyone know if I can parallelize the from_documents function. The embedding process is taking a long time and I was wondering if it can be accomplished in parallel. My code currently is
Plain Text
import chromadb
from llama_index.vector_stores import ChromaVectorStore

db = chromadb.PersistentClient(path="./polygon")
collection = db.get_or_create_collection("default")
vector_store = ChromaVectorStore(chroma_collection=collection)
index = VectorStoreIndex.from_vector_store(vector_store=vector_store)
index = index.from_documents(documents, show_progress=True)
query_engine = index.as_query_engine()

I want to speed up the ingestion of documents
2 comments
e
W
eedk
·

Lamgchain

Quick question. Can you use a langchain loader as a llama index loader? If not, what modification are needed for a valid langchain to llama index conversion?
2 comments
e
L
eedk
·

I have an Agent Tool that fetches web

I have an Agent Tool that fetches web pages. Unfortunately, it sometimes hits token size limit when downloading large web pages. How can I workaround this problem?
2 comments
e
T