drop metadata requirement (#1712)

* drop metadata requirement

* fix linting

* Update docs for new knowledge

* more linting

* more linting

* make save_documents private

* update docs to the new way we use knowledge and include clearing memory
This commit is contained in:
Brandon Hancock (bhancock_ai)
2024-12-05 14:59:52 -05:00
committed by GitHub
parent 7b276e6797
commit c7c0647dd2
11 changed files with 63 additions and 78 deletions

View File

@@ -1,5 +1,5 @@
from abc import ABC, abstractmethod
from typing import List, Dict, Any, Optional
from typing import Any, Dict, List, Optional
import numpy as np
from pydantic import BaseModel, ConfigDict, Field
@@ -17,7 +17,7 @@ class BaseKnowledgeSource(BaseModel, ABC):
model_config = ConfigDict(arbitrary_types_allowed=True)
storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
metadata: Dict[str, Any] = Field(default_factory=dict)
metadata: Dict[str, Any] = Field(default_factory=dict) # Currently unused
collection_name: Optional[str] = Field(default=None)
@abstractmethod
@@ -41,9 +41,9 @@ class BaseKnowledgeSource(BaseModel, ABC):
for i in range(0, len(text), self.chunk_size - self.chunk_overlap)
]
def save_documents(self, metadata: Dict[str, Any]):
def _save_documents(self):
"""
Save the documents to the storage.
This method should be called after the chunks and embeddings are generated.
"""
self.storage.save(self.chunks, metadata)
self.storage.save(self.chunks)