mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-08 15:48:29 +00:00
f89c2bfb7e
Some checks failed
Notify Downstream / notify-downstream (push) Has been cancelled
* fix: support to reset memories after changing Crew's embedder The sources must not be added while initializing the Knowledge otherwise we could not reset it * chore: improve reset memory feedback Previously, even when no memories were actually erased, we logged that they had been. From now on, the log will specify which memory has been reset. * feat: improve get_crew discovery from a single file Crew instances can now be discovered from any function or method with a return type annotation of -> Crew, as well as from module-level attributes assigned to a Crew instance. Additionally, crews can be retrieved from within a Flow * refactor: make add_sources a public method from Knowledge
78 lines
2.4 KiB
Python
78 lines
2.4 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()
|
|
|
|
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.")
|