Spaces:
Runtime error
Runtime error
File size: 9,836 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 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 |
"""Chain for question-answering against a vector database."""
from __future__ import annotations
import inspect
import warnings
from abc import abstractmethod
from typing import Any, Dict, List, Optional
from langchain_core.documents import Document
from langchain_core.language_models import BaseLanguageModel
from langchain_core.prompts import PromptTemplate
from langchain_core.pydantic_v1 import Extra, Field, root_validator
from langchain_core.retrievers import BaseRetriever
from langchain_core.vectorstores import VectorStore
from langchain.callbacks.manager import (
AsyncCallbackManagerForChainRun,
CallbackManagerForChainRun,
Callbacks,
)
from langchain.chains.base import Chain
from langchain.chains.combine_documents.base import BaseCombineDocumentsChain
from langchain.chains.combine_documents.stuff import StuffDocumentsChain
from langchain.chains.llm import LLMChain
from langchain.chains.question_answering import load_qa_chain
from langchain.chains.question_answering.stuff_prompt import PROMPT_SELECTOR
class BaseRetrievalQA(Chain):
"""Base class for question-answering chains."""
combine_documents_chain: BaseCombineDocumentsChain
"""Chain to use to combine the documents."""
input_key: str = "query" #: :meta private:
output_key: str = "result" #: :meta private:
return_source_documents: bool = False
"""Return the source documents or not."""
class Config:
"""Configuration for this pydantic object."""
extra = Extra.forbid
arbitrary_types_allowed = True
allow_population_by_field_name = True
@property
def input_keys(self) -> List[str]:
"""Input keys.
:meta private:
"""
return [self.input_key]
@property
def output_keys(self) -> List[str]:
"""Output keys.
:meta private:
"""
_output_keys = [self.output_key]
if self.return_source_documents:
_output_keys = _output_keys + ["source_documents"]
return _output_keys
@classmethod
def from_llm(
cls,
llm: BaseLanguageModel,
prompt: Optional[PromptTemplate] = None,
callbacks: Callbacks = None,
**kwargs: Any,
) -> BaseRetrievalQA:
"""Initialize from LLM."""
_prompt = prompt or PROMPT_SELECTOR.get_prompt(llm)
llm_chain = LLMChain(llm=llm, prompt=_prompt, callbacks=callbacks)
document_prompt = PromptTemplate(
input_variables=["page_content"], template="Context:\n{page_content}"
)
combine_documents_chain = StuffDocumentsChain(
llm_chain=llm_chain,
document_variable_name="context",
document_prompt=document_prompt,
callbacks=callbacks,
)
return cls(
combine_documents_chain=combine_documents_chain,
callbacks=callbacks,
**kwargs,
)
@classmethod
def from_chain_type(
cls,
llm: BaseLanguageModel,
chain_type: str = "stuff",
chain_type_kwargs: Optional[dict] = None,
**kwargs: Any,
) -> BaseRetrievalQA:
"""Load chain from chain type."""
_chain_type_kwargs = chain_type_kwargs or {}
combine_documents_chain = load_qa_chain(
llm, chain_type=chain_type, **_chain_type_kwargs
)
return cls(combine_documents_chain=combine_documents_chain, **kwargs)
@abstractmethod
def _get_docs(
self,
question: str,
*,
run_manager: CallbackManagerForChainRun,
) -> List[Document]:
"""Get documents to do question answering over."""
def _call(
self,
inputs: Dict[str, Any],
run_manager: Optional[CallbackManagerForChainRun] = None,
) -> Dict[str, Any]:
"""Run get_relevant_text and llm on input query.
If chain has 'return_source_documents' as 'True', returns
the retrieved documents as well under the key 'source_documents'.
Example:
.. code-block:: python
res = indexqa({'query': 'This is my query'})
answer, docs = res['result'], res['source_documents']
"""
_run_manager = run_manager or CallbackManagerForChainRun.get_noop_manager()
question = inputs[self.input_key]
accepts_run_manager = (
"run_manager" in inspect.signature(self._get_docs).parameters
)
if accepts_run_manager:
docs = self._get_docs(question, run_manager=_run_manager)
else:
docs = self._get_docs(question) # type: ignore[call-arg]
answer = self.combine_documents_chain.run(
input_documents=docs, question=question, callbacks=_run_manager.get_child()
)
if self.return_source_documents:
return {self.output_key: answer, "source_documents": docs}
else:
return {self.output_key: answer}
@abstractmethod
async def _aget_docs(
self,
question: str,
*,
run_manager: AsyncCallbackManagerForChainRun,
) -> List[Document]:
"""Get documents to do question answering over."""
async def _acall(
self,
inputs: Dict[str, Any],
run_manager: Optional[AsyncCallbackManagerForChainRun] = None,
) -> Dict[str, Any]:
"""Run get_relevant_text and llm on input query.
If chain has 'return_source_documents' as 'True', returns
the retrieved documents as well under the key 'source_documents'.
Example:
.. code-block:: python
res = indexqa({'query': 'This is my query'})
answer, docs = res['result'], res['source_documents']
"""
_run_manager = run_manager or AsyncCallbackManagerForChainRun.get_noop_manager()
question = inputs[self.input_key]
accepts_run_manager = (
"run_manager" in inspect.signature(self._aget_docs).parameters
)
if accepts_run_manager:
docs = await self._aget_docs(question, run_manager=_run_manager)
else:
docs = await self._aget_docs(question) # type: ignore[call-arg]
answer = await self.combine_documents_chain.arun(
input_documents=docs, question=question, callbacks=_run_manager.get_child()
)
if self.return_source_documents:
return {self.output_key: answer, "source_documents": docs}
else:
return {self.output_key: answer}
class RetrievalQA(BaseRetrievalQA):
"""Chain for question-answering against an index.
Example:
.. code-block:: python
from langchain.llms import OpenAI
from langchain.chains import RetrievalQA
from langchain.vectorstores import FAISS
from langchain_core.vectorstores import VectorStoreRetriever
retriever = VectorStoreRetriever(vectorstore=FAISS(...))
retrievalQA = RetrievalQA.from_llm(llm=OpenAI(), retriever=retriever)
"""
retriever: BaseRetriever = Field(exclude=True)
def _get_docs(
self,
question: str,
*,
run_manager: CallbackManagerForChainRun,
) -> List[Document]:
"""Get docs."""
return self.retriever.get_relevant_documents(
question, callbacks=run_manager.get_child()
)
async def _aget_docs(
self,
question: str,
*,
run_manager: AsyncCallbackManagerForChainRun,
) -> List[Document]:
"""Get docs."""
return await self.retriever.aget_relevant_documents(
question, callbacks=run_manager.get_child()
)
@property
def _chain_type(self) -> str:
"""Return the chain type."""
return "retrieval_qa"
class VectorDBQA(BaseRetrievalQA):
"""Chain for question-answering against a vector database."""
vectorstore: VectorStore = Field(exclude=True, alias="vectorstore")
"""Vector Database to connect to."""
k: int = 4
"""Number of documents to query for."""
search_type: str = "similarity"
"""Search type to use over vectorstore. `similarity` or `mmr`."""
search_kwargs: Dict[str, Any] = Field(default_factory=dict)
"""Extra search args."""
@root_validator()
def raise_deprecation(cls, values: Dict) -> Dict:
warnings.warn(
"`VectorDBQA` is deprecated - "
"please use `from langchain.chains import RetrievalQA`"
)
return values
@root_validator()
def validate_search_type(cls, values: Dict) -> Dict:
"""Validate search type."""
if "search_type" in values:
search_type = values["search_type"]
if search_type not in ("similarity", "mmr"):
raise ValueError(f"search_type of {search_type} not allowed.")
return values
def _get_docs(
self,
question: str,
*,
run_manager: CallbackManagerForChainRun,
) -> List[Document]:
"""Get docs."""
if self.search_type == "similarity":
docs = self.vectorstore.similarity_search(
question, k=self.k, **self.search_kwargs
)
elif self.search_type == "mmr":
docs = self.vectorstore.max_marginal_relevance_search(
question, k=self.k, **self.search_kwargs
)
else:
raise ValueError(f"search_type of {self.search_type} not allowed.")
return docs
async def _aget_docs(
self,
question: str,
*,
run_manager: AsyncCallbackManagerForChainRun,
) -> List[Document]:
"""Get docs."""
raise NotImplementedError("VectorDBQA does not support async")
@property
def _chain_type(self) -> str:
"""Return the chain type."""
return "vector_db_qa"
|