From 8f24808c8a39763b823bd85f643390ca458c7a5c Mon Sep 17 00:00:00 2001 From: seehi <6580@pm.me> Date: Wed, 22 Nov 2023 14:25:07 +0800 Subject: [PATCH] make examples/search_kb.py work --- examples/search_kb.py | 26 +++++++++++++++++++++---- metagpt/actions/search_and_summarize.py | 1 - metagpt/document_store/faiss_store.py | 18 ++++++++++------- metagpt/roles/sales.py | 23 +++++++++++----------- 4 files changed, 44 insertions(+), 24 deletions(-) diff --git a/examples/search_kb.py b/examples/search_kb.py index b6f7d87a0..7a9911ca2 100644 --- a/examples/search_kb.py +++ b/examples/search_kb.py @@ -5,22 +5,40 @@ """ import asyncio +from metagpt.actions import Action from metagpt.const import DATA_PATH from metagpt.document_store import FaissStore from metagpt.logs import logger from metagpt.roles import Sales +from metagpt.schema import Message + +""" example.json, e.g. +[ + { + "source": "Which facial cleanser is good for oily skin?", + "output": "ABC cleanser is preferred by many with oily skin." + }, + { + "source": "Is L'Oreal good to use?", + "output": "L'Oreal is a popular brand with many positive reviews." + } +] +""" async def search(): - store = FaissStore(DATA_PATH / 'example.json') + store = FaissStore(DATA_PATH / "example.json") role = Sales(profile="Sales", store=store) - - queries = ["Which facial cleanser is good for oily skin?", "Is L'Oreal good to use?"] + role._watch({Action}) + queries = [ + Message("Which facial cleanser is good for oily skin?", cause_by=Action), + Message("Is L'Oreal good to use?", cause_by=Action), + ] for query in queries: logger.info(f"User: {query}") result = await role.run(query) logger.info(result) -if __name__ == '__main__': +if __name__ == "__main__": asyncio.run(search()) diff --git a/metagpt/actions/search_and_summarize.py b/metagpt/actions/search_and_summarize.py index 069f2a977..5e4cdaea0 100644 --- a/metagpt/actions/search_and_summarize.py +++ b/metagpt/actions/search_and_summarize.py @@ -140,4 +140,3 @@ class SearchAndSummarize(Action): logger.debug(prompt) logger.debug(result) return result - \ No newline at end of file diff --git a/metagpt/document_store/faiss_store.py b/metagpt/document_store/faiss_store.py index dd450010d..5c6459179 100644 --- a/metagpt/document_store/faiss_store.py +++ b/metagpt/document_store/faiss_store.py @@ -5,6 +5,7 @@ @Author : alexanderwu @File : faiss_store.py """ +import asyncio import pickle from pathlib import Path from typing import Optional @@ -20,7 +21,7 @@ from metagpt.logs import logger class FaissStore(LocalStore): - def __init__(self, raw_data: Path, cache_dir=None, meta_col='source', content_col='output'): + def __init__(self, raw_data: Path, cache_dir=None, meta_col="source", content_col="output"): self.meta_col = meta_col self.content_col = content_col super().__init__(raw_data, cache_dir) @@ -50,7 +51,7 @@ class FaissStore(LocalStore): pickle.dump(store, f) store.index = index - def search(self, query, expand_cols=False, sep='\n', *args, k=5, **kwargs): + def search(self, query, expand_cols=False, sep="\n", *args, k=5, **kwargs): rsp = self.store.similarity_search(query, k=k, **kwargs) logger.debug(rsp) if expand_cols: @@ -58,6 +59,9 @@ class FaissStore(LocalStore): else: return str(sep.join([f"{x.page_content}" for x in rsp])) + async def asearch(self, *args, **kwargs): + return await asyncio.to_thread(self.search, *args, **kwargs) + def write(self): """Initialize the index and library based on the Document (JSON / XLSX, etc.) file provided by the user.""" if not self.raw_data.exists(): @@ -78,8 +82,8 @@ class FaissStore(LocalStore): raise NotImplementedError -if __name__ == '__main__': - faiss_store = FaissStore(DATA_PATH / 'qcs/qcs_4w.json') - logger.info(faiss_store.search('Oily Skin Facial Cleanser')) - faiss_store.add([f'Oily Skin Facial Cleanser-{i}' for i in range(3)]) - logger.info(faiss_store.search('Oily Skin Facial Cleanser')) +if __name__ == "__main__": + faiss_store = FaissStore(DATA_PATH / "qcs/qcs_4w.json") + logger.info(faiss_store.search("Oily Skin Facial Cleanser")) + faiss_store.add([f"Oily Skin Facial Cleanser-{i}" for i in range(3)]) + logger.info(faiss_store.search("Oily Skin Facial Cleanser")) diff --git a/metagpt/roles/sales.py b/metagpt/roles/sales.py index a45ad6f1b..d5aac1824 100644 --- a/metagpt/roles/sales.py +++ b/metagpt/roles/sales.py @@ -12,24 +12,23 @@ from metagpt.tools import SearchEngineType class Sales(Role): def __init__( - self, - name="Xiaomei", - profile="Retail sales guide", - desc="I am a sales guide in retail. My name is Xiaomei. I will answer some customer questions next, and I " - "will answer questions only based on the information in the knowledge base." - "If I feel that you can't get the answer from the reference material, then I will directly reply that" - " I don't know, and I won't tell you that this is from the knowledge base," - "but pretend to be what I know. Note that each of my replies will be replied in the tone of a " - "professional guide", - store=None + self, + name="Xiaomei", + profile="Retail sales guide", + desc="I am a sales guide in retail. My name is Xiaomei. I will answer some customer questions next, and I " + "will answer questions only based on the information in the knowledge base." + "If I feel that you can't get the answer from the reference material, then I will directly reply that" + " I don't know, and I won't tell you that this is from the knowledge base," + "but pretend to be what I know. Note that each of my replies will be replied in the tone of a " + "professional guide", + store=None, ): super().__init__(name, profile, desc=desc) self._set_store(store) def _set_store(self, store): if store: - action = SearchAndSummarize("", engine=SearchEngineType.CUSTOM_ENGINE, search_func=store.search) + action = SearchAndSummarize("", engine=SearchEngineType.CUSTOM_ENGINE, search_func=store.asearch) else: action = SearchAndSummarize() self._init_actions([action]) - \ No newline at end of file