Skip to content

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Enhance QdrantVectorSearchTool (#3806)

Daniel Barreto70b083945fd0
diff --git a/docs/en/tools/database-data/qdrantvectorsearchtool.mdx b/docs/en/tools/database-data/qdrantvectorsearchtool.mdx
index 8a6491ca9..1cba50d2e 100644
--- a/docs/en/tools/database-data/qdrantvectorsearchtool.mdx
+++ b/docs/en/tools/database-data/qdrantvectorsearchtool.mdx
@@ -23,13 +23,15 @@ Here's a minimal example of how to use the tool:
```python
from crewai import Agent
-from crewai_tools import QdrantVectorSearchTool
+from crewai_tools import QdrantVectorSearchTool, QdrantConfig
-# Initialize the tool
+# Initialize the tool with QdrantConfig
qdrant_tool = QdrantVectorSearchTool(
- qdrant_url="your_qdrant_url",
- qdrant_api_key="your_qdrant_api_key",
- collection_name="your_collection"
+ qdrant_config=QdrantConfig(
+ qdrant_url="your_qdrant_url",
+ qdrant_api_key="your_qdrant_api_key",
+ collection_name="your_collection"
+ )
)
# Create an agent that uses the tool
@@ -82,7 +84,7 @@ def extract_text_from_pdf(pdf_path):
def get_openai_embedding(text):
response = client.embeddings.create(
input=text,
- model="text-embedding-3-small"
+ model="text-embedding-3-large"
)
return response.data[0].embedding
@@ -90,13 +92,13 @@ def get_openai_embedding(text):
def load_pdf_to_qdrant(pdf_path, qdrant, collection_name):
# Extract text from PDF
text_chunks = extract_text_from_pdf(pdf_path)
-
+
# Create Qdrant collection
if qdrant.collection_exists(collection_name):
qdrant.delete_collection(collection_name)
qdrant.create_collection(
collection_name=collection_name,
- vectors_config=VectorParams(size=1536, distance=Distance.COSINE)
+ vectors_config=VectorParams(size=3072, distance=Distance.COSINE)
)
# Store embeddings
@@ -120,19 +122,23 @@ pdf_path = "path/to/your/document.pdf"
load_pdf_to_qdrant(pdf_path, qdrant, collection_name)
# Initialize Qdrant search tool
+from crewai_tools import QdrantConfig
+
qdrant_tool = QdrantVectorSearchTool(
- qdrant_url=os.getenv("QDRANT_URL"),
- qdrant_api_key=os.getenv("QDRANT_API_KEY"),
- collection_name=collection_name,
- limit=3,
- score_threshold=0.35
+ qdrant_config=QdrantConfig(
+ qdrant_url=os.getenv("QDRANT_URL"),
+ qdrant_api_key=os.getenv("QDRANT_API_KEY"),
+ collection_name=collection_name,
+ limit=3,
+ score_threshold=0.35
+ )
)
# Create CrewAI agents
search_agent = Agent(
role="Senior Semantic Search Agent",
goal="Find and analyze documents based on semantic search",
- backstory="""You are an expert research assistant who can find relevant
+ backstory="""You are an expert research assistant who can find relevant
information using semantic search in a Qdrant database.""",
tools=[qdrant_tool],
verbose=True
@@ -141,7 +147,7 @@ search_agent = Agent(
answer_agent = Agent(
role="Senior Answer Assistant",
goal="Generate answers to questions based on the context provided",
- backstory="""You are an expert answer assistant who can generate
+ backstory="""You are an expert answer assistant who can generate
answers to questions based on the context provided.""",
tools=[qdrant_tool],
verbose=True
@@ -180,21 +186,82 @@ print(result)
## Tool Parameters
### Required Parameters
+- `qdrant_config` (QdrantConfig): Configuration object containing all Qdrant settings
+
+### QdrantConfig Parameters
- `qdrant_url` (str): The URL of your Qdrant server
-- `qdrant_api_key` (str): API key for authentication with Qdrant
+- `qdrant_api_key` (str, optional): API key for authentication with Qdrant
- `collection_name` (str): Name of the Qdrant collection to search
-
-### Optional Parameters
- `limit` (int): Maximum number of results to return (default: 3)
- `score_threshold` (float): Minimum similarity score threshold (default: 0.35)
+- `filter` (Any, optional): Qdrant Filter instance for advanced filtering (default: None)
+
+### Optional Tool Parameters
- `custom_embedding_fn` (Callable[[str], list[float]]): Custom function for text vectorization
+- `qdrant_package` (str): Base package path for Qdrant (default: "qdrant_client")
+- `client` (Any): Pre-initialized Qdrant client (optional)
+
+## Advanced Filtering
+
+The QdrantVectorSearchTool supports powerful filtering capabilities to refine your search results:
+
+### Dynamic Filtering
+Use `filter_by` and `filter_value` parameters in your search to filter results on-the-fly:
+
+```python
+# Agent will use these parameters when calling the tool
+# The tool schema accepts filter_by and filter_value
+# Example: search with category filter
+# Results will be filtered where category == "technology"
+```
+
+### Preset Filters with QdrantConfig
+For complex filtering, use Qdrant Filter instances in your configuration:
+
+```python
+from qdrant_client.http import models as qmodels
+from crewai_tools import QdrantVectorSearchTool, QdrantConfig
+
+# Create a filter for specific conditions
+preset_filter = qmodels.Filter(
+ must=[
+ qmodels.FieldCondition(
+ key="category",
+ match=qmodels.MatchValue(value="research")
+ ),
+ qmodels.FieldCondition(
+ key="year",
+ match=qmodels.MatchValue(value=2024)
+ )
+ ]
+)
+
+# Initialize tool with preset filter
+qdrant_tool = QdrantVectorSearchTool(
+ qdrant_config=QdrantConfig(
+ qdrant_url="your_url",
+ qdrant_api_key="your_key",
+ collection_name="your_collection",
+ filter=preset_filter # Preset filter applied to all searches
+ )
+)
+```
+
+### Combining Filters
+The tool automatically combines preset filters from `QdrantConfig` with dynamic filters from `filter_by` and `filter_value`:
+
+```python
+# If QdrantConfig has a preset filter for category="research"
+# And the search uses filter_by="year", filter_value=2024
+# Both filters will be combined (AND logic)
+```
## Search Parameters
The tool accepts these parameters in its schema:
- `query` (str): The search query to find similar documents
- `filter_by` (str, optional): Metadata field to filter on
-- `filter_value` (str, optional): Value to filter by
+- `filter_value` (Any, optional): Value to filter by
## Return Format
@@ -214,7 +281,7 @@ The tool returns results in JSON format:
## Default Embedding
-By default, the tool uses OpenAI's `text-embedding-3-small` model for vectorization. This requires:
+By default, the tool uses OpenAI's `text-embedding-3-large` model for vectorization. This requires:
- OpenAI API key set in environment: `OPENAI_API_KEY`
## Custom Embeddings
@@ -240,18 +307,22 @@ def custom_embeddings(text: str) -> list[float]:
# Tokenize and get model outputs
inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
outputs = model(**inputs)
-
+
# Use mean pooling to get text embedding
embeddings = outputs.last_hidden_state.mean(dim=1)
-
+
# Convert to list of floats and return
return embeddings[0].tolist()
# Use custom embeddings with the tool
+from crewai_tools import QdrantConfig
+
tool = QdrantVectorSearchTool(
- qdrant_url="your_url",
- qdrant_api_key="your_key",
- collection_name="your_collection",
+ qdrant_config=QdrantConfig(
+ qdrant_url="your_url",
+ qdrant_api_key="your_key",
+ collection_name="your_collection"
+ ),
custom_embedding_fn=custom_embeddings # Pass your custom function
)
```
@@ -269,4 +340,4 @@ Required environment variables:
```bash
export QDRANT_URL="your_qdrant_url" # If not provided in constructor
export QDRANT_API_KEY="your_api_key" # If not provided in constructor
-export OPENAI_API_KEY="your_openai_key" # If using default embeddings
\ No newline at end of file
+export OPENAI_API_KEY="your_openai_key" # If using default embeddings
diff --git a/docs/ko/tools/database-data/qdrantvectorsearchtool.mdx b/docs/ko/tools/database-data/qdrantvectorsearchtool.mdx
index 96da58686..247c1b765 100644
--- a/docs/ko/tools/database-data/qdrantvectorsearchtool.mdx
+++ b/docs/ko/tools/database-data/qdrantvectorsearchtool.mdx
@@ -23,13 +23,15 @@ uv add qdrant-client
```python
from crewai import Agent
-from crewai_tools import QdrantVectorSearchTool
+from crewai_tools import QdrantVectorSearchTool, QdrantConfig
-# Initialize the tool
+# QdrantConfig로 도구 초기화
qdrant_tool = QdrantVectorSearchTool(
- qdrant_url="your_qdrant_url",
- qdrant_api_key="your_qdrant_api_key",
- collection_name="your_collection"
+ qdrant_config=QdrantConfig(
+ qdrant_url="your_qdrant_url",
+ qdrant_api_key="your_qdrant_api_key",
+ collection_name="your_collection"
+ )
)
# Create an agent that uses the tool
@@ -82,7 +84,7 @@ def extract_text_from_pdf(pdf_path):
def get_openai_embedding(text):
response = client.embeddings.create(
input=text,
- model="text-embedding-3-small"
+ model="text-embedding-3-large"
)
return response.data[0].embedding
@@ -90,13 +92,13 @@ def get_openai_embedding(text):
def load_pdf_to_qdrant(pdf_path, qdrant, collection_name):
# Extract text from PDF
text_chunks = extract_text_from_pdf(pdf_path)
-
+
# Create Qdrant collection
if qdrant.collection_exists(collection_name):
qdrant.delete_collection(collection_name)
qdrant.create_collection(
collection_name=collection_name,
- vectors_config=VectorParams(size=1536, distance=Distance.COSINE)
+ vectors_config=VectorParams(size=3072, distance=Distance.COSINE)
)
# Store embeddings
@@ -120,19 +122,23 @@ pdf_path = "path/to/your/document.pdf"
load_pdf_to_qdrant(pdf_path, qdrant, collection_name)
# Initialize Qdrant search tool
+from crewai_tools import QdrantConfig
+
qdrant_tool = QdrantVectorSearchTool(
- qdrant_url=os.getenv("QDRANT_URL"),
- qdrant_api_key=os.getenv("QDRANT_API_KEY"),
- collection_name=collection_name,
- limit=3,
- score_threshold=0.35
+ qdrant_config=QdrantConfig(
+ qdrant_url=os.getenv("QDRANT_URL"),
+ qdrant_api_key=os.getenv("QDRANT_API_KEY"),
+ collection_name=collection_name,
+ limit=3,
+ score_threshold=0.35
+ )
)
# Create CrewAI agents
search_agent = Agent(
role="Senior Semantic Search Agent",
goal="Find and analyze documents based on semantic search",
- backstory="""You are an expert research assistant who can find relevant
+ backstory="""You are an expert research assistant who can find relevant
information using semantic search in a Qdrant database.""",
tools=[qdrant_tool],
verbose=True
@@ -141,7 +147,7 @@ search_agent = Agent(
answer_agent = Agent(
role="Senior Answer Assistant",
goal="Generate answers to questions based on the context provided",
- backstory="""You are an expert answer assistant who can generate
+ backstory="""You are an expert answer assistant who can generate
answers to questions based on the context provided.""",
tools=[qdrant_tool],
verbose=True
@@ -180,21 +186,82 @@ print(result)
## 도구 매개변수
### 필수 파라미터
+- `qdrant_config` (QdrantConfig): 모든 Qdrant 설정을 포함하는 구성 객체
+
+### QdrantConfig 매개변수
- `qdrant_url` (str): Qdrant 서버의 URL
-- `qdrant_api_key` (str): Qdrant 인증을 위한 API 키
+- `qdrant_api_key` (str, 선택 사항): Qdrant 인증을 위한 API 키
- `collection_name` (str): 검색할 Qdrant 컬렉션의 이름
-
-### 선택적 매개변수
- `limit` (int): 반환할 최대 결과 수 (기본값: 3)
- `score_threshold` (float): 최소 유사도 점수 임계값 (기본값: 0.35)
+- `filter` (Any, 선택 사항): 고급 필터링을 위한 Qdrant Filter 인스턴스 (기본값: None)
+
+### 선택적 도구 매개변수
- `custom_embedding_fn` (Callable[[str], list[float]]): 텍스트 벡터화를 위한 사용자 지정 함수
+- `qdrant_package` (str): Qdrant의 기본 패키지 경로 (기본값: "qdrant_client")
+- `client` (Any): 사전 초기화된 Qdrant 클라이언트 (선택 사항)
+
+## 고급 필터링
+
+QdrantVectorSearchTool은 검색 결과를 세밀하게 조정할 수 있는 강력한 필터링 기능을 지원합니다:
+
+### 동적 필터링
+검색 시 `filter_by` 및 `filter_value` 매개변수를 사용하여 즉석에서 결과를 필터링할 수 있습니다:
+
+```python
+# 에이전트는 도구를 호출할 때 이러한 매개변수를 사용합니다
+# 도구 스키마는 filter_by 및 filter_value를 허용합니다
+# 예시: 카테고리 필터를 사용한 검색
+# 결과는 category == "기술"인 항목으로 필터링됩니다
+```
+
+### QdrantConfig를 사용한 사전 설정 필터
+복잡한 필터링의 경우 구성에서 Qdrant Filter 인스턴스를 사용하세요:
+
+```python
+from qdrant_client.http import models as qmodels
+from crewai_tools import QdrantVectorSearchTool, QdrantConfig
+
+# 특정 조건에 대한 필터 생성
+preset_filter = qmodels.Filter(
+ must=[
+ qmodels.FieldCondition(
+ key="category",
+ match=qmodels.MatchValue(value="research")
+ ),
+ qmodels.FieldCondition(
+ key="year",
+ match=qmodels.MatchValue(value=2024)
+ )
+ ]
+)
+
+# 사전 설정 필터로 도구 초기화
+qdrant_tool = QdrantVectorSearchTool(
+ qdrant_config=QdrantConfig(
+ qdrant_url="your_url",
+ qdrant_api_key="your_key",
+ collection_name="your_collection",
+ filter=preset_filter # 모든 검색에 적용되는 사전 설정 필터
+ )
+)
+```
+
+### 필터 결합
+도구는 `QdrantConfig`의 사전 설정 필터와 `filter_by` 및 `filter_value`의 동적 필터를 자동으로 결합합니다:
+
+```python
+# QdrantConfig에 category="research"에 대한 사전 설정 필터가 있고
+# 검색에서 filter_by="year", filter_value=2024를 사용하는 경우
+# 두 필터가 모두 결합됩니다 (AND 논리)
+```
## 검색 매개변수
이 도구는 스키마에서 다음과 같은 매개변수를 허용합니다:
- `query` (str): 유사한 문서를 찾기 위한 검색 쿼리
- `filter_by` (str, 선택 사항): 필터링할 메타데이터 필드
-- `filter_value` (str, 선택 사항): 필터 기준 값
+- `filter_value` (Any, 선택 사항): 필터 기준 값
## 반환 형식
@@ -214,7 +281,7 @@ print(result)
## 기본 임베딩
-기본적으로, 이 도구는 벡터화를 위해 OpenAI의 `text-embedding-3-small` 모델을 사용합니다. 이를 위해서는 다음이 필요합니다:
+기본적으로, 이 도구는 벡터화를 위해 OpenAI의 `text-embedding-3-large` 모델을 사용합니다. 이를 위해서는 다음이 필요합니다:
- 환경변수에 설정된 OpenAI API 키: `OPENAI_API_KEY`
## 커스텀 임베딩
@@ -240,18 +307,22 @@ def custom_embeddings(text: str) -> list[float]:
# Tokenize and get model outputs
inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
outputs = model(**inputs)
-
+
# Use mean pooling to get text embedding
embeddings = outputs.last_hidden_state.mean(dim=1)
-
+
# Convert to list of floats and return
return embeddings[0].tolist()
# Use custom embeddings with the tool
+from crewai_tools import QdrantConfig
+
tool = QdrantVectorSearchTool(
- qdrant_url="your_url",
- qdrant_api_key="your_key",
- collection_name="your_collection",
+ qdrant_config=QdrantConfig(
+ qdrant_url="your_url",
+ qdrant_api_key="your_key",
+ collection_name="your_collection"
+ ),
custom_embedding_fn=custom_embeddings # Pass your custom function
)
```
@@ -270,4 +341,4 @@ tool = QdrantVectorSearchTool(
export QDRANT_URL="your_qdrant_url" # If not provided in constructor
export QDRANT_API_KEY="your_api_key" # If not provided in constructor
export OPENAI_API_KEY="your_openai_key" # If using default embeddings
-```
\ No newline at end of file
+```
diff --git a/docs/pt-BR/tools/database-data/qdrantvectorsearchtool.mdx b/docs/pt-BR/tools/database-data/qdrantvectorsearchtool.mdx
index 5c56a93d0..bb8504485 100644
--- a/docs/pt-BR/tools/database-data/qdrantvectorsearchtool.mdx
+++ b/docs/pt-BR/tools/database-data/qdrantvectorsearchtool.mdx
@@ -23,13 +23,15 @@ Veja um exemplo mínimo de como utilizar a ferramenta:
```python
from crewai import Agent
-from crewai_tools import QdrantVectorSearchTool
+from crewai_tools import QdrantVectorSearchTool, QdrantConfig
-# Inicialize a ferramenta
+# Inicialize a ferramenta com QdrantConfig
qdrant_tool = QdrantVectorSearchTool(
- qdrant_url="your_qdrant_url",
- qdrant_api_key="your_qdrant_api_key",
- collection_name="your_collection"
+ qdrant_config=QdrantConfig(
+ qdrant_url="your_qdrant_url",
+ qdrant_api_key="your_qdrant_api_key",
+ collection_name="your_collection"
+ )
)
# Crie um agente que utiliza a ferramenta
@@ -82,7 +84,7 @@ def extract_text_from_pdf(pdf_path):
def get_openai_embedding(text):
response = client.embeddings.create(
input=text,
- model="text-embedding-3-small"
+ model="text-embedding-3-large"
)
return response.data[0].embedding
@@ -90,13 +92,13 @@ def get_openai_embedding(text):
def load_pdf_to_qdrant(pdf_path, qdrant, collection_name):
# Extrair texto do PDF
text_chunks = extract_text_from_pdf(pdf_path)
-
+
# Criar coleção no Qdrant
if qdrant.collection_exists(collection_name):
qdrant.delete_collection(collection_name)
qdrant.create_collection(
collection_name=collection_name,
- vectors_config=VectorParams(size=1536, distance=Distance.COSINE)
+ vectors_config=VectorParams(size=3072, distance=Distance.COSINE)
)
# Armazenar embeddings
@@ -120,19 +122,23 @@ pdf_path = "path/to/your/document.pdf"
load_pdf_to_qdrant(pdf_path, qdrant, collection_name)
# Inicializar ferramenta de busca Qdrant
+from crewai_tools import QdrantConfig
+
qdrant_tool = QdrantVectorSearchTool(
- qdrant_url=os.getenv("QDRANT_URL"),
- qdrant_api_key=os.getenv("QDRANT_API_KEY"),
- collection_name=collection_name,
- limit=3,
- score_threshold=0.35
+ qdrant_config=QdrantConfig(
+ qdrant_url=os.getenv("QDRANT_URL"),
+ qdrant_api_key=os.getenv("QDRANT_API_KEY"),
+ collection_name=collection_name,
+ limit=3,
+ score_threshold=0.35
+ )
)
# Criar agentes CrewAI
search_agent = Agent(
role="Senior Semantic Search Agent",
goal="Find and analyze documents based on semantic search",
- backstory="""You are an expert research assistant who can find relevant
+ backstory="""You are an expert research assistant who can find relevant
information using semantic search in a Qdrant database.""",
tools=[qdrant_tool],
verbose=True
@@ -141,7 +147,7 @@ search_agent = Agent(
answer_agent = Agent(
role="Senior Answer Assistant",
goal="Generate answers to questions based on the context provided",
- backstory="""You are an expert answer assistant who can generate
+ backstory="""You are an expert answer assistant who can generate
answers to questions based on the context provided.""",
tools=[qdrant_tool],
verbose=True
@@ -180,21 +186,82 @@ print(result)
## Parâmetros da Ferramenta
### Parâmetros Obrigatórios
+- `qdrant_config` (QdrantConfig): Objeto de configuração contendo todas as configurações do Qdrant
+
+### Parâmetros do QdrantConfig
- `qdrant_url` (str): URL do seu servidor Qdrant
-- `qdrant_api_key` (str): Chave de API para autenticação com o Qdrant
+- `qdrant_api_key` (str, opcional): Chave de API para autenticação com o Qdrant
- `collection_name` (str): Nome da coleção Qdrant a ser pesquisada
-
-### Parâmetros Opcionais
- `limit` (int): Número máximo de resultados a serem retornados (padrão: 3)
- `score_threshold` (float): Limite mínimo de similaridade (padrão: 0.35)
+- `filter` (Any, opcional): Instância de Filter do Qdrant para filtragem avançada (padrão: None)
+
+### Parâmetros Opcionais da Ferramenta
- `custom_embedding_fn` (Callable[[str], list[float]]): Função personalizada para vetorização de textos
+- `qdrant_package` (str): Caminho base do pacote Qdrant (padrão: "qdrant_client")
+- `client` (Any): Cliente Qdrant pré-inicializado (opcional)
+
+## Filtragem Avançada
+
+A ferramenta QdrantVectorSearchTool oferece recursos poderosos de filtragem para refinar os resultados da busca:
+
+### Filtragem Dinâmica
+Use os parâmetros `filter_by` e `filter_value` na sua busca para filtrar resultados dinamicamente:
+
+```python
+# O agente usará esses parâmetros ao chamar a ferramenta
+# O schema da ferramenta aceita filter_by e filter_value
+# Exemplo: busca com filtro de categoria
+# Os resultados serão filtrados onde categoria == "tecnologia"
+```
+
+### Filtros Pré-definidos com QdrantConfig
+Para filtragens complexas, use instâncias de Filter do Qdrant na sua configuração:
+
+```python
+from qdrant_client.http import models as qmodels
+from crewai_tools import QdrantVectorSearchTool, QdrantConfig
+
+# Criar um filtro para condições específicas
+preset_filter = qmodels.Filter(
+ must=[
+ qmodels.FieldCondition(
+ key="categoria",
+ match=qmodels.MatchValue(value="pesquisa")
+ ),
+ qmodels.FieldCondition(
+ key="ano",
+ match=qmodels.MatchValue(value=2024)
+ )
+ ]
+)
+
+# Inicializar ferramenta com filtro pré-definido
+qdrant_tool = QdrantVectorSearchTool(
+ qdrant_config=QdrantConfig(
+ qdrant_url="your_url",
+ qdrant_api_key="your_key",
+ collection_name="your_collection",
+ filter=preset_filter # Filtro pré-definido aplicado a todas as buscas
+ )
+)
+```
+
+### Combinando Filtros
+A ferramenta combina automaticamente os filtros pré-definidos do `QdrantConfig` com os filtros dinâmicos de `filter_by` e `filter_value`:
+
+```python
+# Se QdrantConfig tem um filtro pré-definido para categoria="pesquisa"
+# E a busca usa filter_by="ano", filter_value=2024
+# Ambos os filtros serão combinados (lógica AND)
+```
## Parâmetros de Busca
A ferramenta aceita estes parâmetros em seu schema:
- `query` (str): Consulta de busca para encontrar documentos similares
- `filter_by` (str, opcional): Campo de metadado para filtrar
-- `filter_value` (str, opcional): Valor para filtrar
+- `filter_value` (Any, opcional): Valor para filtrar
## Formato de Retorno
@@ -214,7 +281,7 @@ A ferramenta retorna resultados no formato JSON:
## Embedding Padrão
-Por padrão, a ferramenta utiliza o modelo `text-embedding-3-small` da OpenAI para vetorização. Isso requer:
+Por padrão, a ferramenta utiliza o modelo `text-embedding-3-large` da OpenAI para vetorização. Isso requer:
- Chave de API da OpenAI definida na variável de ambiente: `OPENAI_API_KEY`
## Embeddings Personalizados
@@ -240,18 +307,22 @@ def custom_embeddings(text: str) -> list[float]:
# Tokenizar e obter saídas do modelo
inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
outputs = model(**inputs)
-
+
# Usar mean pooling para obter o embedding do texto
embeddings = outputs.last_hidden_state.mean(dim=1)
-
+
# Converter para lista de floats e retornar
return embeddings[0].tolist()
# Usar embeddings personalizados com a ferramenta
+from crewai_tools import QdrantConfig
+
tool = QdrantVectorSearchTool(
- qdrant_url="your_url",
- qdrant_api_key="your_key",
- collection_name="your_collection",
+ qdrant_config=QdrantConfig(
+ qdrant_url="your_url",
+ qdrant_api_key="your_key",
+ collection_name="your_collection"
+ ),
custom_embedding_fn=custom_embeddings # Passe sua função personalizada
)
```
@@ -270,4 +341,4 @@ Variáveis de ambiente obrigatórias:
export QDRANT_URL="your_qdrant_url" # Se não for informado no construtor
export QDRANT_API_KEY="your_api_key" # Se não for informado no construtor
export OPENAI_API_KEY="your_openai_key" # Se estiver usando embeddings padrão
-```
\ No newline at end of file
+```
diff --git a/lib/crewai-tools/src/crewai_tools/tools/qdrant_vector_search_tool/qdrant_search_tool.py b/lib/crewai-tools/src/crewai_tools/tools/qdrant_vector_search_tool/qdrant_search_tool.py
index adcb733a5..b0b4d1a77 100644
--- a/lib/crewai-tools/src/crewai_tools/tools/qdrant_vector_search_tool/qdrant_search_tool.py
+++ b/lib/crewai-tools/src/crewai_tools/tools/qdrant_vector_search_tool/qdrant_search_tool.py
@@ -1,9 +1,9 @@
from __future__ import annotations
+from collections.abc import Callable
import importlib
import json
import os
-from collections.abc import Callable
from typing import Any
from crewai.tools import BaseTool, EnvVar
@@ -12,9 +12,13 @@ from pydantic.types import ImportString
class QdrantToolSchema(BaseModel):
- query: str = Field(..., description="Query to search in Qdrant DB.")
- filter_by: str | None = None
- filter_value: str | None = None
+ query: str = Field(..., description="Query to search in Qdrant DB")
+ filter_by: str | None = Field(
+ default=None, description="Parameter to filter the search by."
+ )
+ filter_value: Any | None = Field(
+ default=None, description="Value to filter the search by."
+ )
class QdrantConfig(BaseModel):
@@ -25,7 +29,9 @@ class QdrantConfig(BaseModel):
collection_name: str
limit: int = 3
score_threshold: float = 0.35
- filter_conditions: list[tuple[str, Any]] = Field(default_factory=list)
+ filter: Any | None = Field(
+ default=None, description="Qdrant Filter instance for advanced filtering."
+ )
class QdrantVectorSearchTool(BaseTool):
@@ -76,23 +82,26 @@ class QdrantVectorSearchTool(BaseTool):
filter_value: Any | None = None,
) -> str:
"""Perform vector similarity search."""
- filter_ = self.qdrant_package.http.models.Filter
- field_condition = self.qdrant_package.http.models.FieldCondition
- match_value = self.qdrant_package.http.models.MatchValue
- conditions = self.qdrant_config.filter_conditions.copy()
- if filter_by and filter_value is not None:
- conditions.append((filter_by, filter_value))
search_filter = (
- filter_(
- must=[
- field_condition(key=k, match=match_value(value=v))
- for k, v in conditions
- ]
- )
- if conditions
- else None
+ self.qdrant_config.filter.model_copy()
+ if self.qdrant_config.filter is not None
+ else self.qdrant_package.http.models.Filter(must=[])
)
+ if filter_by and filter_value is not None:
+ if not hasattr(search_filter, "must") or not isinstance(
+ search_filter.must, list
+ ):
+ search_filter.must = []
+ search_filter.must.append(
+ self.qdrant_package.http.models.FieldCondition(
+ key=filter_by,
+ match=self.qdrant_package.http.models.MatchValue(
+ value=filter_value
+ ),
+ )
+ )
+
query_vector = (
self.custom_embedding_fn(query)
if self.custom_embedding_fn