mirror of
https://github.com/hwchase17/langchain
synced 2024-11-10 01:10:59 +00:00
bc7e56e8df
Supporting asyncio in langchain primitives allows for users to run them concurrently and creates more seamless integration with asyncio-supported frameworks (FastAPI, etc.) Summary of changes: **LLM** * Add `agenerate` and `_agenerate` * Implement in OpenAI by leveraging `client.Completions.acreate` **Chain** * Add `arun`, `acall`, `_acall` * Implement them in `LLMChain` and `LLMMathChain` for now **Agent** * Refactor and leverage async chain and llm methods * Add ability for `Tools` to contain async coroutine * Implement async SerpaPI `arun` Create demo notebook. Open questions: * Should all the async stuff go in separate classes? I've seen both patterns (keeping the same class and having async and sync methods vs. having class separation)
63 lines
1.9 KiB
Python
63 lines
1.9 KiB
Python
"""Test HyDE."""
|
|
from typing import List, Optional
|
|
|
|
import numpy as np
|
|
from pydantic import BaseModel
|
|
|
|
from langchain.chains.hyde.base import HypotheticalDocumentEmbedder
|
|
from langchain.chains.hyde.prompts import PROMPT_MAP
|
|
from langchain.embeddings.base import Embeddings
|
|
from langchain.llms.base import BaseLLM
|
|
from langchain.schema import Generation, LLMResult
|
|
|
|
|
|
class FakeEmbeddings(Embeddings):
|
|
"""Fake embedding class for tests."""
|
|
|
|
def embed_documents(self, texts: List[str]) -> List[List[float]]:
|
|
"""Return random floats."""
|
|
return [list(np.random.uniform(0, 1, 10)) for _ in range(10)]
|
|
|
|
def embed_query(self, text: str) -> List[float]:
|
|
"""Return random floats."""
|
|
return list(np.random.uniform(0, 1, 10))
|
|
|
|
|
|
class FakeLLM(BaseLLM, BaseModel):
|
|
"""Fake LLM wrapper for testing purposes."""
|
|
|
|
n: int = 1
|
|
|
|
def _generate(
|
|
self, prompts: List[str], stop: Optional[List[str]] = None
|
|
) -> LLMResult:
|
|
return LLMResult(generations=[[Generation(text="foo") for _ in range(self.n)]])
|
|
|
|
async def _agenerate(
|
|
self, prompts: List[str], stop: Optional[List[str]] = None
|
|
) -> LLMResult:
|
|
return LLMResult(generations=[[Generation(text="foo") for _ in range(self.n)]])
|
|
|
|
@property
|
|
def _llm_type(self) -> str:
|
|
"""Return type of llm."""
|
|
return "fake"
|
|
|
|
|
|
def test_hyde_from_llm() -> None:
|
|
"""Test loading HyDE from all prompts."""
|
|
for key in PROMPT_MAP:
|
|
embedding = HypotheticalDocumentEmbedder.from_llm(
|
|
FakeLLM(), FakeEmbeddings(), key
|
|
)
|
|
embedding.embed_query("foo")
|
|
|
|
|
|
def test_hyde_from_llm_with_multiple_n() -> None:
|
|
"""Test loading HyDE from all prompts."""
|
|
for key in PROMPT_MAP:
|
|
embedding = HypotheticalDocumentEmbedder.from_llm(
|
|
FakeLLM(n=8), FakeEmbeddings(), key
|
|
)
|
|
embedding.embed_query("foo")
|