mirror of
https://github.com/crewAIInc/crewAI.git
synced 2025-12-15 20:08:29 +00:00
Enhance QdrantVectorSearchTool (#3806)
Some checks failed
Some checks failed
This commit is contained in:
Daniel Barreto
@@ -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_url` (str): The URL of your Qdrant server
|
||||
- `qdrant_api_key` (str): API key for authentication with Qdrant
|
||||
- `collection_name` (str): Name of the Qdrant collection to search
|
||||
- `qdrant_config` (QdrantConfig): Configuration object containing all Qdrant settings
|
||||
|
||||
### Optional Parameters
|
||||
### QdrantConfig Parameters
|
||||
- `qdrant_url` (str): The URL of your Qdrant server
|
||||
- `qdrant_api_key` (str, optional): API key for authentication with Qdrant
|
||||
- `collection_name` (str): Name of the Qdrant collection to search
|
||||
- `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
|
||||
export OPENAI_API_KEY="your_openai_key" # If using default embeddings
|
||||
|
||||
@@ -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_url` (str): Qdrant 서버의 URL
|
||||
- `qdrant_api_key` (str): Qdrant 인증을 위한 API 키
|
||||
- `collection_name` (str): 검색할 Qdrant 컬렉션의 이름
|
||||
- `qdrant_config` (QdrantConfig): 모든 Qdrant 설정을 포함하는 구성 객체
|
||||
|
||||
### 선택적 매개변수
|
||||
### QdrantConfig 매개변수
|
||||
- `qdrant_url` (str): Qdrant 서버의 URL
|
||||
- `qdrant_api_key` (str, 선택 사항): Qdrant 인증을 위한 API 키
|
||||
- `collection_name` (str): 검색할 Qdrant 컬렉션의 이름
|
||||
- `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
|
||||
```
|
||||
```
|
||||
|
||||
@@ -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_url` (str): URL do seu servidor Qdrant
|
||||
- `qdrant_api_key` (str): Chave de API para autenticação com o Qdrant
|
||||
- `collection_name` (str): Nome da coleção Qdrant a ser pesquisada
|
||||
- `qdrant_config` (QdrantConfig): Objeto de configuração contendo todas as configurações do Qdrant
|
||||
|
||||
### Parâmetros Opcionais
|
||||
### Parâmetros do QdrantConfig
|
||||
- `qdrant_url` (str): URL do seu servidor Qdrant
|
||||
- `qdrant_api_key` (str, opcional): Chave de API para autenticação com o Qdrant
|
||||
- `collection_name` (str): Nome da coleção Qdrant a ser pesquisada
|
||||
- `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
|
||||
```
|
||||
```
|
||||
|
||||
Reference in New Issue
Block a user