github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-08-13 14:50:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(docs): handle collection not found error on RAG tutorial when qdrant is selected as vectorStore (#32099)

Browse Source 
In [Rag Part 1
Tutorial](https://python.langchain.com/docs/tutorials/rag/), when QDrant
vector store is selected, the sample code does not work
It fails with error  `ValueError: Collection test not found`

So, this fix is creating that collection and ensuring its dimension size
is matching the selection the embedding size of the selected LLM Model

---------

Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
This commit is contained in:
Yasien Dwieb 2025-08-11 23:31:24 +03:00 committed by GitHub
parent f9b4e501a8
commit 155e3740bc
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/src/theme/VectorStoreTabs.js
View File

@ -77,7 +77,7 @@ export default function VectorStoreTabs(props) {
{
value: "Qdrant",
label: "Qdrant",
text: `from langchain_qdrant import QdrantVectorStore\nfrom qdrant_client import QdrantClient\n${useFakeEmbeddings ? fakeEmbeddingsString : ""}\nclient = QdrantClient(":memory:")\n${vectorStoreVarName} = QdrantVectorStore(\n client=client,\n collection_name="test",\n embedding=embeddings,\n)`,
text: `from qdrant_client.models import Distance, VectorParams\nfrom langchain_qdrant import QdrantVectorStore\nfrom qdrant_client import QdrantClient\n${useFakeEmbeddings ? fakeEmbeddingsString : ""}\nclient = QdrantClient(":memory:")\n\nvector_size = len(embeddings.embed_query("sample text"))\n\nif not client.collection_exists("test"):\n client.create_collection(\n collection_name="test",\n vectors_config=VectorParams(size=vector_size, distance=Distance.COSINE)\n )\n${vectorStoreVarName} = QdrantVectorStore(\n client=client,\n collection_name="test",\n embedding=embeddings,\n)`,
packageName: "langchain-qdrant",
default: false,
},