Spaces:
Runtime error
Runtime error
File size: 3,383 Bytes
129cd69 |
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 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 |
from typing import Any, Dict, List, Optional, Type
from langchain_core.documents import Document
from langchain_core.embeddings import Embeddings
from langchain_core.language_models import BaseLanguageModel
from langchain_core.pydantic_v1 import BaseModel, Extra, Field
from langchain_core.vectorstores import VectorStore
from langchain.chains.qa_with_sources.retrieval import RetrievalQAWithSourcesChain
from langchain.chains.retrieval_qa.base import RetrievalQA
from langchain.document_loaders.base import BaseLoader
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.llms.openai import OpenAI
from langchain.text_splitter import RecursiveCharacterTextSplitter, TextSplitter
from langchain.vectorstores.chroma import Chroma
def _get_default_text_splitter() -> TextSplitter:
return RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
class VectorStoreIndexWrapper(BaseModel):
"""Wrapper around a vectorstore for easy access."""
vectorstore: VectorStore
class Config:
"""Configuration for this pydantic object."""
extra = Extra.forbid
arbitrary_types_allowed = True
def query(
self,
question: str,
llm: Optional[BaseLanguageModel] = None,
retriever_kwargs: Optional[Dict[str, Any]] = None,
**kwargs: Any,
) -> str:
"""Query the vectorstore."""
llm = llm or OpenAI(temperature=0)
retriever_kwargs = retriever_kwargs or {}
chain = RetrievalQA.from_chain_type(
llm, retriever=self.vectorstore.as_retriever(**retriever_kwargs), **kwargs
)
return chain.run(question)
def query_with_sources(
self,
question: str,
llm: Optional[BaseLanguageModel] = None,
retriever_kwargs: Optional[Dict[str, Any]] = None,
**kwargs: Any,
) -> dict:
"""Query the vectorstore and get back sources."""
llm = llm or OpenAI(temperature=0)
retriever_kwargs = retriever_kwargs or {}
chain = RetrievalQAWithSourcesChain.from_chain_type(
llm, retriever=self.vectorstore.as_retriever(**retriever_kwargs), **kwargs
)
return chain({chain.question_key: question})
class VectorstoreIndexCreator(BaseModel):
"""Logic for creating indexes."""
vectorstore_cls: Type[VectorStore] = Chroma
embedding: Embeddings = Field(default_factory=OpenAIEmbeddings)
text_splitter: TextSplitter = Field(default_factory=_get_default_text_splitter)
vectorstore_kwargs: dict = Field(default_factory=dict)
class Config:
"""Configuration for this pydantic object."""
extra = Extra.forbid
arbitrary_types_allowed = True
def from_loaders(self, loaders: List[BaseLoader]) -> VectorStoreIndexWrapper:
"""Create a vectorstore index from loaders."""
docs = []
for loader in loaders:
docs.extend(loader.load())
return self.from_documents(docs)
def from_documents(self, documents: List[Document]) -> VectorStoreIndexWrapper:
"""Create a vectorstore index from documents."""
sub_docs = self.text_splitter.split_documents(documents)
vectorstore = self.vectorstore_cls.from_documents(
sub_docs, self.embedding, **self.vectorstore_kwargs
)
return VectorStoreIndexWrapper(vectorstore=vectorstore)
|