[Question]: Add new documents in an existing collection in Qdrant Vector Store

To add new documents to an existing collection in Qdrant Vector Store, you can use the add method of the QdrantVectorStore class. Here’s a step-by-step guide:

Create a Qdrant client: Initialize the Qdrant client to interact with the Qdrant instance.
Initialize the QdrantVectorStore: Create an instance of QdrantVectorStore with the existing collection name.
Create a list of TextNode objects: Each TextNode should contain the text, unique ID, relationships, metadata, and embeddings.
Add the nodes to the Qdrant collection: Use the add method of the QdrantVectorStore instance to add the new nodes.

Here is an example code snippet:

from llama_index.legacy.schema import TextNode, NodeRelationship, RelatedNodeInfo
from llama_index.legacy.vector_stores import QdrantVectorStore
import qdrant_client

# Step 1: Create a Qdrant client
client = qdrant_client.QdrantClient(":memory:")

# Step 2: Initialize the QdrantVectorStore with the existing collection name
qdrant_vector_store = QdrantVectorStore(collection_name="existing_collection", client=client)

# Step 3: Create a list of TextNode objects with embeddings
new_node_embeddings = [
    TextNode(
        text="new document text 1",
        id_="new-doc-id-1",
        relationships={NodeRelationship.SOURCE: RelatedNodeInfo(node_id="source-id-1")},
        metadata={
            "author": "Author Name",
            "theme": "Theme",
        },
        embedding=[0.5, 0.5],  # Example embedding
    ),
    TextNode(
        text="new document text 2",
        id_="new-doc-id-2",
        relationships={NodeRelationship.SOURCE: RelatedNodeInfo(node_id="source-id-2")},
        metadata={
            "author": "Another Author",
            "theme": "Another Theme",
        },
        embedding=[0.2, 0.8],  # Example embedding
    ),
]

# Step 4: Add the new nodes to the Qdrant collection
qdrant_vector_store.add(new_node_embeddings)

This will add the new documents to the existing collection, and if the collection is not already initialized, it will be created with the appropriate vector size.

#### Details

**Sources** - [llama-index-legacy/llama_index/legacy/vector_stores/qdrant.py](https://github.com/run-llama/llama_index/blob/main/llama-index-legacy/llama_index/legacy/vector_stores/qdrant.py) - [llama-index-integrations/vector_stores/llama-index-vector-stores-qdrant/llama_index/vector_stores/qdrant/base.py](https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/vector_stores/llama-index-vector-stores-qdrant/llama_index/vector_stores/qdrant/base.py) - [llama-index-legacy/tests/vector_stores/test_qdrant.py](https://github.com/run-llama/llama_index/blob/main/llama-index-legacy/tests/vector_stores/test_qdrant.py) - [docs/docs/examples/vector_stores/qdrant_hybrid.ipynb](https://github.com/run-llama/llama_index/blob/main/docs/docs/examples/vector_stores/qdrant_hybrid.ipynb) - [llama-index-integrations/vector_stores/llama-index-vector-stores-qdrant/tests/test_vector_stores_qdrant.py](https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/vector_stores/llama-index-vector-stores-qdrant/tests/test_vector_stores_qdrant.py)
**About Dosu** This response is meant to be useful and save you time. It is **not meant to be a precise solution**, but rather a starting point for your own research. Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

To continue the conversation, mention @dosu.

run-llama / llama_index

[Question]: Add new documents in an existing collection in Qdrant Vector Store #13653

Question Validation

Question