Repository navigation
Replies: 2 comments
|
Hi @Arturs! Yes, you can pass your |
0 replies
|
You specify your collection name ( When the collection from haystack import Pipeline
from haystack.components.embedders import SentenceTransformersTextEmbedder
from haystack_integrations.document_stores.weaviate import WeaviateDocumentStore
from haystack_integrations.components.retrievers.weaviate import WeaviateEmbeddingRetriever
# 1. Point WeaviateDocumentStore to your existing "Abc" collection
document_store = WeaviateDocumentStore(
url="http://localhost:8080", # replace with your Weaviate URL / cloud_url + auth_client_secret
collection_settings={
"class": "Abc",
},
)
# 2. Pass that document_store to the retriever in your RAG pipeline
retriever = WeaviateEmbeddingRetriever(document_store=document_store, top_k=5)
rag_pipeline = Pipeline()
rag_pipeline.add_component(
"text_embedder",
SentenceTransformersTextEmbedder(model="sentence-transformers/all-MiniLM-L6-v2"), # match the model used to index "Abc"
)
rag_pipeline.add_component("retriever", retriever)
# ... add your PromptBuilder and Generator here
rag_pipeline.connect("text_embedder.embedding", "retriever.query_embedding")Two things to double-check if
|
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
I have Weaviate collection "Abc" with data which I want to use in my RAG pipeline. Where do I specify that my data source is "Abc"?
All reactions