mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-07 15:18:29 +00:00
311a078ca6
Some checks failed
Notify Downstream / notify-downstream (push) Has been cancelled
* Enhance knowledge management in CrewAI - Added `KnowledgeConfig` class to configure knowledge retrieval parameters such as `limit` and `score_threshold`. - Updated `Agent` and `Crew` classes to utilize the new knowledge configuration for querying knowledge sources. - Enhanced documentation to clarify the addition of knowledge sources at both agent and crew levels. - Introduced new tips in documentation to guide users on knowledge source management and configuration. * Refactor knowledge configuration parameters in CrewAI - Renamed `limit` to `results_limit` in `KnowledgeConfig`, `query_knowledge`, and `query` methods for consistency and clarity. - Updated related documentation to reflect the new parameter name, ensuring users understand the configuration options for knowledge retrieval. * Refactor agent tests to utilize mock knowledge storage - Updated test cases in `agent_test.py` to use `KnowledgeStorage` for mocking knowledge sources, enhancing test reliability and clarity. - Renamed `limit` to `results_limit` in `KnowledgeConfig` for consistency with recent changes. - Ensured that knowledge queries are properly mocked to return expected results during tests. * Add VCR support for agent tests with query limits and score thresholds - Introduced `@pytest.mark.vcr` decorator in `agent_test.py` for tests involving knowledge sources, ensuring consistent recording of HTTP interactions. - Added new YAML cassette files for `test_agent_with_knowledge_sources_with_query_limit_and_score_threshold` and `test_agent_with_knowledge_sources_with_query_limit_and_score_threshold_default`, capturing the expected API responses for these tests. - Enhanced test reliability by utilizing VCR to manage external API calls during testing. * Update documentation to format parameter names in code style - Changed the formatting of `results_limit` and `score_threshold` in the documentation to use code style for better clarity and emphasis. - Ensured consistency in documentation presentation to enhance user understanding of configuration options. * Enhance KnowledgeConfig with field descriptions - Updated `results_limit` and `score_threshold` in `KnowledgeConfig` to use Pydantic's `Field` for improved documentation and clarity. - Added descriptions to both parameters to provide better context for their usage in knowledge retrieval configuration. * docstrings added
79 lines
2.5 KiB
Python
79 lines
2.5 KiB
Python
import os
|
|
from typing import Any, Dict, List, Optional
|
|
|
|
from pydantic import BaseModel, ConfigDict, Field
|
|
|
|
from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
|
|
from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
|
|
|
|
os.environ["TOKENIZERS_PARALLELISM"] = "false" # removes logging from fastembed
|
|
|
|
|
|
class Knowledge(BaseModel):
|
|
"""
|
|
Knowledge is a collection of sources and setup for the vector store to save and query relevant context.
|
|
Args:
|
|
sources: List[BaseKnowledgeSource] = Field(default_factory=list)
|
|
storage: Optional[KnowledgeStorage] = Field(default=None)
|
|
embedder: Optional[Dict[str, Any]] = None
|
|
"""
|
|
|
|
sources: List[BaseKnowledgeSource] = Field(default_factory=list)
|
|
model_config = ConfigDict(arbitrary_types_allowed=True)
|
|
storage: Optional[KnowledgeStorage] = Field(default=None)
|
|
embedder: Optional[Dict[str, Any]] = None
|
|
collection_name: Optional[str] = None
|
|
|
|
def __init__(
|
|
self,
|
|
collection_name: str,
|
|
sources: List[BaseKnowledgeSource],
|
|
embedder: Optional[Dict[str, Any]] = None,
|
|
storage: Optional[KnowledgeStorage] = None,
|
|
**data,
|
|
):
|
|
super().__init__(**data)
|
|
if storage:
|
|
self.storage = storage
|
|
else:
|
|
self.storage = KnowledgeStorage(
|
|
embedder=embedder, collection_name=collection_name
|
|
)
|
|
self.sources = sources
|
|
self.storage.initialize_knowledge_storage()
|
|
self._add_sources()
|
|
|
|
def query(
|
|
self, query: List[str], results_limit: int = 3, score_threshold: float = 0.35
|
|
) -> List[Dict[str, Any]]:
|
|
"""
|
|
Query across all knowledge sources to find the most relevant information.
|
|
Returns the top_k most relevant chunks.
|
|
|
|
Raises:
|
|
ValueError: If storage is not initialized.
|
|
"""
|
|
if self.storage is None:
|
|
raise ValueError("Storage is not initialized.")
|
|
|
|
results = self.storage.search(
|
|
query,
|
|
limit=results_limit,
|
|
score_threshold=score_threshold,
|
|
)
|
|
return results
|
|
|
|
def _add_sources(self):
|
|
try:
|
|
for source in self.sources:
|
|
source.storage = self.storage
|
|
source.add()
|
|
except Exception as e:
|
|
raise e
|
|
|
|
def reset(self) -> None:
|
|
if self.storage:
|
|
self.storage.reset()
|
|
else:
|
|
raise ValueError("Storage is not initialized.")
|