QDrant Search , error for connect distance_func #2517
Labels
bug
Something isn't working
Comments
|
Hey @devalexandre! I'm here to help you with any bugs, questions, or contributions you have regarding the repository. Let's work together to get this sorted out! To resolve the issue with the Here is the relevant part of the code that handles the vs = Qdrant.from_documents(
documents=documents, # type: ignore
embedding=embedding,
api_key=api_key,
collection_name=collection_name,
content_payload_key=content_payload_key,
distance_func=distance_func, # Ensure this parameter is correctly passed
grpc_port=grpc_port,
host=host,
https=https,
location=location,
metadata_payload_key=metadata_payload_key,
path=path,
port=port,
prefer_grpc=prefer_grpc,
prefix=prefix,
timeout=timeout,
url=url,
)Make sure that the In the class QdrantSearchComponent(QdrantVectorStoreComponent, LCVectorStoreComponent):
display_name = "Qdrant Search"
description = "Construct Qdrant wrapper from a list of texts."
icon = "Qdrant"
def build_config(self):
return {
"search_type": {
"display_name": "Search Type",
"options": ["Similarity", "MMR"],
},
"input_value": {"display_name": "Input"},
"embedding": {"display_name": "Embedding"},
"api_key": {"display_name": "API Key", "password": True, "advanced": True},
"collection_name": {"display_name": "Collection Name"},
"content_payload_key": {
"display_name": "Content Payload Key",
"advanced": True,
},
"distance_func": {"display_name": "Distance Function", "advanced": True},
"grpc_port": {"display_name": "gRPC Port", "advanced": True},
"host": {"display_name": "Host", "advanced": True},
"https": {"display_name": "HTTPS", "advanced": True},
"location": {"display_name": "Location", "advanced": True},
"metadata_payload_key": {
"display_name": "Metadata Payload Key",
"advanced": True,
},
"path": {"display_name": "Path", "advanced": True},
"port": {"display_name": "Port", "advanced": True},
"prefer_grpc": {"display_name": "Prefer gRPC", "advanced": True},
"prefix": {"display_name": "Prefix", "advanced": True},
"search_kwargs": {"display_name": "Search Kwargs", "advanced": True},
"timeout": {"display_name": "Timeout", "advanced": True},
"url": {"display_name": "URL", "advanced": True},
"number_of_results": {
"display_name": "Number of Results",
"info": "Number of results to return.",
"advanced": True,
},
}
def build( # type: ignore[override]
self,
input_value: Text,
embedding: Embeddings,
collection_name: str,
number_of_results: int = 4,
search_type: str = "similarity",
api_key: Optional[str] = None,
content_payload_key: str = "page_content",
distance_func: str = "Cosine",
grpc_port: int = 6334,
https: bool = False,
host: Optional[str] = None,
location: Optional[str] = None,
metadata_payload_key: str = "metadata",
path: Optional[str] = None,
port: Optional[int] = 6333,
prefer_grpc: bool = False,
prefix: Optional[str] = None,
search_kwargs: Optional[NestedDict] = None,
timeout: Optional[int] = None,
url: Optional[str] = None,
) -> List[Data]: # type: ignore[override]
vector_store = super().build(
embedding=embedding,
collection_name=collection_name,
api_key=api_key,
content_payload_key=content_payload_key,
distance_func=distance_func,
grpc_port=grpc_port,
https=https,
host=host,
location=location,
metadata_payload_key=metadata_payload_key,
path=path,
port=port,
prefer_grpc=prefer_grpc,
prefix=prefix,
timeout=timeout,
url=url,
)
if not vector_store:
raise ValueError("Failed to load the Qdrant index.")
if search_kwargs is None:
search_kwargs = {}
return self.search_with_vector_store(
vector_store=vector_store,
input_value=input_value,
search_type=search_type,
k=number_of_results,
**search_kwargs,
)Ensure that the |
I try implementation from typing import List
from langchain_community.vectorstores import Qdrant
from langflow.base.vectorstores.model import LCVectorStoreComponent
from langflow.helpers.data import docs_to_data
from langflow.io import (
DropdownInput,
HandleInput,
IntInput,
StrInput,
SecretStrInput,
DataInput,
MultilineInput,
)
from langflow.schema import Data
class QdrantVectorStoreComponent(LCVectorStoreComponent):
display_name = "Qdrant"
description = "Qdrant Vector Store with search capabilities"
documentation = "https://python.langchain.com/docs/modules/data_connection/vectorstores/integrations/qdrant"
icon = "Qdrant"
inputs = [
StrInput(name="collection_name", display_name="Collection Name", required=True),
StrInput(name="host", display_name="Host", value="localhost", advanced=True),
IntInput(name="port", display_name="Port", value=6333, advanced=True),
IntInput(name="grpc_port", display_name="gRPC Port", value=6334, advanced=True),
SecretStrInput(name="api_key", display_name="API Key", advanced=True),
StrInput(name="prefix", display_name="Prefix", advanced=True),
IntInput(name="timeout", display_name="Timeout", advanced=True),
StrInput(name="path", display_name="Path", advanced=True),
StrInput(name="url", display_name="URL", advanced=True),
DropdownInput(
name="distance_func",
display_name="Distance Function",
options=["Cosine", "Euclidean", "Dot Product"],
value="Cosine",
advanced=True,
),
StrInput(name="content_payload_key", display_name="Content Payload Key", value="page_content", advanced=True),
StrInput(name="metadata_payload_key", display_name="Metadata Payload Key", value="metadata", advanced=True),
MultilineInput(name="search_query", display_name="Search Query"),
DataInput(
name="ingest_data",
display_name="Ingest Data",
is_list=True,
),
HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
IntInput(
name="number_of_results",
display_name="Number of Results",
info="Number of results to return.",
value=4,
advanced=True,
),
]
def build_vector_store(self) -> Qdrant:
return self._build_qdrant()
def _build_qdrant(self) -> Qdrant:
qdrant_kwargs = {
"collection_name": self.collection_name,
"content_payload_key": self.content_payload_key,
"metadata_payload_key": self.metadata_payload_key,
"distance_func": self.distance_func,
}
server_kwargs = {
"host": self.host if self.host else None,
"port": int(self.port), # Certifique-se de que port é um número inteiro
"grpc_port": int(self.grpc_port), # Certifique-se de que grpc_port é um número inteiro
"api_key": self.api_key,
"prefix": self.prefix,
"timeout": int(self.timeout) if self.timeout else None, # Certifique-se de que timeout é um número inteiro
"path": self.path if self.path else None,
"url": self.url if self.url else None,
}
server_kwargs = {k: v for k, v in server_kwargs.items() if v is not None}
documents = []
for _input in self.ingest_data or []:
if isinstance(_input, Data):
documents.append(_input.to_lc_document())
else:
documents.append(_input)
from langchain.embeddings.base import Embeddings # Certifique-se de que esta importação está correta
embedding = self.embedding
if not isinstance(embedding, Embeddings):
raise ValueError("Invalid embedding object")
if documents:
qdrant = Qdrant.from_documents(documents, embedding=embedding, **qdrant_kwargs)
else:
from qdrant_client import QdrantClient
client = QdrantClient(**server_kwargs)
qdrant = Qdrant(embedding_function=embedding.embed_query, client=client, **qdrant_kwargs)
return qdrant
def search_documents(self) -> List[Data]:
vector_store = self._build_qdrant()
if self.search_query and isinstance(self.search_query, str) and self.search_query.strip():
docs = vector_store.similarity_search(
query=self.search_query,
k=self.number_of_results,
)
data = docs_to_data(docs)
self.status = data
return data
else:
return []but display same error 🚨 |
|
The issue you're encountering is due to the Here's the corrected implementation for your
Here is the updated code: from typing import List
from langchain_community.vectorstores import Qdrant
from langflow.base.vectorstores.model import LCVectorStoreComponent
from langflow.helpers.data import docs_to_data
from langflow.io import (
DropdownInput,
HandleInput,
IntInput,
StrInput,
SecretStrInput,
DataInput,
MultilineInput,
)
from langflow.schema import Data
class QdrantVectorStoreComponent(LCVectorStoreComponent):
display_name = "Qdrant"
description = "Qdrant Vector Store with search capabilities"
documentation = "<link url='https://python.langchain.com/docs/modules/data_connection/vectorstores/integrations/qdrant'>Webpage description not available.</link>"
icon = "Qdrant"
inputs = [
StrInput(name="collection_name", display_name="Collection Name", required=True),
StrInput(name="host", display_name="Host", value="localhost", advanced=True),
IntInput(name="port", display_name="Port", value=6333, advanced=True),
IntInput(name="grpc_port", display_name="gRPC Port", value=6334, advanced=True),
SecretStrInput(name="api_key", display_name="API Key", advanced=True),
StrInput(name="prefix", display_name="Prefix", advanced=True),
IntInput(name="timeout", display_name="Timeout", advanced=True),
StrInput(name="path", display_name="Path", advanced=True),
StrInput(name="url", display_name="URL", advanced=True),
DropdownInput(
name="distance_func",
display_name="Distance Function",
options=["Cosine", "Euclidean", "Dot Product"],
value="Cosine",
advanced=True,
),
StrInput(name="content_payload_key", display_name="Content Payload Key", value="page_content", advanced=True),
StrInput(name="metadata_payload_key", display_name="Metadata Payload Key", value="metadata", advanced=True),
MultilineInput(name="search_query", display_name="Search Query"),
DataInput(
name="ingest_data",
display_name="Ingest Data",
is_list=True,
),
HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
IntInput(
name="number_of_results",
display_name="Number of Results",
info="Number of results to return.",
value=4,
advanced=True,
),
]
def build_vector_store(self) -> Qdrant:
return self._build_qdrant()
def _build_qdrant(self) -> Qdrant:
qdrant_kwargs = {
"collection_name": self.collection_name,
"content_payload_key": self.content_payload_key,
"metadata_payload_key": self.metadata_payload_key,
}
server_kwargs = {
"host": self.host if self.host else None,
"port": int(self.port), # Ensure port is an integer
"grpc_port": int(self.grpc_port), # Ensure grpc_port is an integer
"api_key": self.api_key,
"prefix": self.prefix,
"timeout": int(self.timeout) if self.timeout else None, # Ensure timeout is an integer
"path": self.path if self.path else None,
"url": self.url if self.url else None,
}
server_kwargs = {k: v for k, v in server_kwargs.items() if v is not None}
documents = []
for _input in self.ingest_data or []:
if isinstance(_input, Data):
documents.append(_input.to_lc_document())
else:
documents.append(_input)
from langchain.embeddings.base import Embeddings # Ensure this import is correct
embedding = self.embedding
if not isinstance(embedding, Embeddings):
raise ValueError("Invalid embedding object")
if documents:
qdrant = Qdrant.from_documents(documents, embedding=embedding, **qdrant_kwargs)
else:
from qdrant_client import QdrantClient
client = QdrantClient(**server_kwargs)
qdrant = Qdrant(embedding_function=embedding.embed_query, client=client, **qdrant_kwargs)
return qdrant
def search_documents(self) -> List[Data]:
vector_store = self._build_qdrant()
if self.search_query and isinstance(self.search_query, str) and self.search_query.strip():
docs = vector_store.similarity_search(
query=self.search_query,
k=self.number_of_results,
)
data = docs_to_data(docs)
self.status = data
return data
else:
return []This should resolve the issue with the |
I think that component are imcoplete because now display error |
|
finally work, the final code. from typing import List
from langchain_community.vectorstores import Qdrant
from langflow.base.vectorstores.model import LCVectorStoreComponent
from langflow.helpers.data import docs_to_data
from langflow.io import (
DropdownInput,
HandleInput,
IntInput,
StrInput,
SecretStrInput,
DataInput,
MultilineInput,
)
from langflow.schema import Data
class QdrantVectorStoreComponent(LCVectorStoreComponent):
display_name = "Qdrant"
description = "Qdrant Vector Store with search capabilities"
documentation = "<link url='https://python.langchain.com/docs/modules/data_connection/vectorstores/integrations/qdrant'>Webpage description not available.</link>"
icon = "Qdrant"
inputs = [
StrInput(name="collection_name", display_name="Collection Name", required=True),
StrInput(name="host", display_name="Host", value="localhost", advanced=True),
IntInput(name="port", display_name="Port", value=6333, advanced=True),
IntInput(name="grpc_port", display_name="gRPC Port", value=6334, advanced=True),
SecretStrInput(name="api_key", display_name="API Key", advanced=True),
StrInput(name="prefix", display_name="Prefix", advanced=True),
IntInput(name="timeout", display_name="Timeout", advanced=True),
StrInput(name="path", display_name="Path", advanced=True),
StrInput(name="url", display_name="URL", advanced=True),
DropdownInput(
name="distance_func",
display_name="Distance Function",
options=["Cosine", "Euclidean", "Dot Product"],
value="Cosine",
advanced=True,
),
StrInput(name="content_payload_key", display_name="Content Payload Key", value="page_content", advanced=True),
StrInput(name="metadata_payload_key", display_name="Metadata Payload Key", value="metadata", advanced=True),
MultilineInput(name="search_query", display_name="Search Query"),
DataInput(
name="ingest_data",
display_name="Ingest Data",
is_list=True,
),
HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
IntInput(
name="number_of_results",
display_name="Number of Results",
info="Number of results to return.",
value=4,
advanced=True,
),
]
def build_vector_store(self) -> Qdrant:
return self._build_qdrant()
def _build_qdrant(self) -> Qdrant:
qdrant_kwargs = {
"collection_name": self.collection_name,
"content_payload_key": self.content_payload_key,
"metadata_payload_key": self.metadata_payload_key,
}
server_kwargs = {
"host": self.host if self.host else None,
"port": int(self.port), # Ensure port is an integer
"grpc_port": int(self.grpc_port), # Ensure grpc_port is an integer
"api_key": self.api_key,
"prefix": self.prefix,
"timeout": int(self.timeout) if self.timeout else None, # Ensure timeout is an integer
"path": self.path if self.path else None,
"url": self.url if self.url else None,
}
server_kwargs = {k: v for k, v in server_kwargs.items() if v is not None}
documents = []
for _input in self.ingest_data or []:
if isinstance(_input, Data):
documents.append(_input.to_lc_document())
else:
documents.append(_input)
from langchain.embeddings.base import Embeddings # Ensure this import is correct
embedding = self.embedding
if not isinstance(embedding, Embeddings):
raise ValueError("Invalid embedding object")
if documents:
qdrant = Qdrant.from_documents(documents, embedding=embedding, **qdrant_kwargs)
else:
from qdrant_client import QdrantClient
client = QdrantClient(**server_kwargs)
qdrant = Qdrant(embeddings=embedding.embed_query, client=client, **qdrant_kwargs)
return qdrant
def search_documents(self) -> List[Data]:
vector_store = self._build_qdrant()
if self.search_query and isinstance(self.search_query, str) and self.search_query.strip():
docs = vector_store.similarity_search(
query=self.search_query,
k=self.number_of_results,
)
data = docs_to_data(docs)
self.status = data
return data
else:
return []
``` |
devalexandre
added a commit
to devalexandre/langflow
that referenced
this issue
Jul 3, 2024
fixed embeddings and distance_func for search_documents issue langflow-ai#2517
ogabrielluiz
added a commit
that referenced
this issue
Jul 6, 2024
* Update Qdrant.py fixed embeddings and distance_func for search_documents issue #2517 * [autofix.ci] apply automated fixes * fixed documents link * update params Qdrant * Update Qdrant.py * Update Qdrant.py * Update Qdrant.py * [autofix.ci] apply automated fixes * Update args * [autofix.ci] apply automated fixes --------- Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com> Co-authored-by: Gabriel Luiz Freitas Almeida <[email protected]>
ogabrielluiz
added a commit
to yaitec/langflow
that referenced
this issue
Jul 9, 2024
…i#2518) * Update Qdrant.py fixed embeddings and distance_func for search_documents issue langflow-ai#2517 * [autofix.ci] apply automated fixes * fixed documents link * update params Qdrant * Update Qdrant.py * Update Qdrant.py * Update Qdrant.py * [autofix.ci] apply automated fixes * Update args * [autofix.ci] apply automated fixes --------- Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com> Co-authored-by: Gabriel Luiz Freitas Almeida <[email protected]>
nicoloboschi
pushed a commit
to datastax/ragstack-ai-langflow
that referenced
this issue
Jul 10, 2024
…i#2518) * Update Qdrant.py fixed embeddings and distance_func for search_documents issue langflow-ai#2517 * [autofix.ci] apply automated fixes * fixed documents link * update params Qdrant * Update Qdrant.py * Update Qdrant.py * Update Qdrant.py * [autofix.ci] apply automated fixes * Update args * [autofix.ci] apply automated fixes --------- Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com> Co-authored-by: Gabriel Luiz Freitas Almeida <[email protected]> (cherry picked from commit 6257a32)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Describe the bug
I try use Qrant Search and broken
To Reproduce
Steps to reproduce the behavior:
Screenshots
If applicable, add screenshots to help explain your problem.
Additional context
log:
The text was updated successfully, but these errors were encountered: