Spaces:
Sleeping
Sleeping
File size: 2,356 Bytes
e71c4e6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 |
from typing import List, Type
from langchain.docstore.document import Document
from langchain.embeddings import OpenAIEmbeddings
from langchain.embeddings.base import Embeddings
from langchain.vectorstores import VectorStore
from langchain.vectorstores.faiss import FAISS
from .debug import FakeEmbeddings, FakeVectorStore
from .parsing import File
class FolderIndex:
"""Index for a collection of files (a folder)"""
def __init__(self, files: List[File], index: VectorStore):
self.name: str = "default"
self.files = files
self.index: VectorStore = index
@staticmethod
def _combine_files(files: List[File]) -> List[Document]:
"""Combines all the documents in a list of files into a single list."""
all_texts = []
for file in files:
for doc in file.docs:
doc.metadata["file_name"] = file.name
doc.metadata["file_id"] = file.id
all_texts.append(doc)
return all_texts
@classmethod
def from_files(
cls, files: List[File], embeddings: Embeddings, vector_store: Type[VectorStore]
) -> "FolderIndex":
"""Creates an index from files."""
all_docs = cls._combine_files(files)
index = vector_store.from_documents(
documents=all_docs,
embedding=embeddings,
)
return cls(files=files, index=index)
def embed_files(
files: List[File], embedding: str, vector_store: str, **kwargs
) -> FolderIndex:
"""Embeds a collection of files and stores them in a FolderIndex."""
supported_embeddings: dict[str, Type[Embeddings]] = {
"openai": OpenAIEmbeddings,
"debug": FakeEmbeddings,
}
supported_vector_stores: dict[str, Type[VectorStore]] = {
"faiss": FAISS,
"debug": FakeVectorStore,
}
if embedding in supported_embeddings:
_embeddings = supported_embeddings[embedding](**kwargs)
else:
raise NotImplementedError(f"Embedding {embedding} not supported.")
if vector_store in supported_vector_stores:
_vector_store = supported_vector_stores[vector_store]
else:
raise NotImplementedError(f"Vector store {vector_store} not supported.")
return FolderIndex.from_files(
files=files, embeddings=_embeddings, vector_store=_vector_store
)
|