Unable to retrieve similarity results.

[CHIRU98]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

from langchain_community.document_loaders import TextLoader
from langchain_openai import OpenAIEmbeddings
from langchain_qdrant import QdrantVectorStore
from langchain_text_splitters import CharacterTextSplitter

loader = TextLoader("test_file.txt")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

embedding = OpenAIEmbeddings()


from langchain_qdrant import FastEmbedSparse, RetrievalMode

sparse_embeddings = FastEmbedSparse(model_name="Qdrant/bm25")

url="http://localhost:6333"

qdrant = QdrantVectorStore.from_documents(
    docs,
    embedding=embedding,
    url=url,
    sparse_embedding=sparse_embeddings,
    collection_name="Hybrid_TEST",
    retrieval_mode=RetrievalMode.HYBRID,
    force_recreate=True,
)

query = "what is ?"
# found_docs = qdrant.similarity_search(query)
similar_docs = qdrant.similarity_search_with_score(query)

print(similar_docs)

Description

When i pass the query, i am not getting the reponse. Currently I am getting the reponse as

"qdrant_client.http.exceptions.UnexpectedResponse: Unexpected Response: 404 (Not Found)
Raw response content:
b'' "

System Info

langchain==0.2.10
langchain-community==0.2.9
langchain-core==0.2.22
langchain-openai==0.1.17
langchain-qdrant==0.1.2
langchain-text-splitters==0.2.2

[dosubot[bot]]

The "Unexpected Response: 404 (Not Found)" error typically indicates that the specified collection does not exist in Qdrant or the Qdrant server is not accessible at the provided URL. Here are a few steps to resolve this issue:

1. Verify Collection Name: Ensure that the collection_name ("Hybrid_TEST") exists in your Qdrant instance.

2. Check Qdrant Server: Make sure the Qdrant server is running and accessible at http://localhost:6333.

3. Correct Usage of QdrantVectorStore: Ensure that the QdrantVectorStore is correctly set up to create or access the collection. Here is an example of how to use the QdrantVectorStore class correctly:

from langchain_community.document_loaders import TextLoader
from langchain_openai import OpenAIEmbeddings
from langchain_qdrant import QdrantVectorStore
from langchain_text_splitters import CharacterTextSplitter
from langchain_qdrant import FastEmbedSparse, RetrievalMode

# Load and split documents
loader = TextLoader("test_file.txt")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

# Initialize embeddings
embedding = OpenAIEmbeddings()
sparse_embeddings = FastEmbedSparse(model_name="Qdrant/bm25")

# Qdrant server URL
url = "http://localhost:6333"

# Create or access the Qdrant collection
qdrant = QdrantVectorStore.from_documents(
    docs,
    embedding=embedding,
    url=url,
    sparse_embedding=sparse_embeddings,
    collection_name="Hybrid_TEST",
    retrieval_mode=RetrievalMode.HYBRID,
    force_recreate=True,
)

# Perform similarity search
query = "what is ?"
similar_docs = qdrant.similarity_search_with_score(query)

print(similar_docs)

4. Check Qdrant Collection Creation: If the collection does not exist, ensure that the force_recreate=True parameter is correctly used to create the collection.

5. Qdrant Configuration: Ensure that the Qdrant configuration is correct, including the vectors_config and other parameters if needed.

By following these steps, you should be able to resolve the "404 (Not Found)" error and get the similarity search results ^[1][2].

To continue talking to Dosu, mention @dosu.