topdog/supersonic
1
0
Fork 0
mirror of https://github.com/tencentmusic/supersonic.git synced 2025-12-13 04:57:28 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

add auto-CoT feature (#483)

Browse Source 
* 1.refactor the retrieval module. 2.refactor the http service module. 3.upgrade text2sql output format the parse for absolute time related expression in query.

* fix bug.

* upgrade the config module, now support config llm suppoted by langchain.

* fix conflicts.

* update text2sql config reload to be compitable with new config format.

* modify default config.

* 1.add self-consistency feature for text2sql. 2.upgrade llm api call from sync to async. 3.refactor text2sql module. 4. refactor semantical retriever modules.

* merege with upstream master

* add general retrieve service.

* add api service for sql_agent for crud opereations of few-shots examples.

* modify requirements

* add auto-cot feature

---------

Co-authored-by: shaoweigong <shaoweigong@tencent.com>
This commit is contained in:
codescracker
2023-12-11 16:07:49 +08:00
committed by GitHub
parent 3ae720ef30
commit d79f73eab6
21 changed files with 1822 additions and 565 deletions
Download Patch File Download Diff File Expand all files Collapse all files

63
chat/python/services/s2ql/run.py Normal file
View File

@@ -0,0 +1,63 @@
# -*- coding:utf-8 -*-
import asyncio
import os
import sys
sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
sys.path.append(os.path.dirname(os.path.abspath(__file__)))
import json
from s2ql.constructor import FewShotPromptTemplate2
from s2ql.sql_agent import Text2DSLAgent, Text2DSLAgentAutoCoT, Text2DSLAgentWrapper
from instances.llm_instance import llm
from instances.chromadb_instance import client as chromadb_client
from instances.logging_instance import logger
from instances.text2vec_instance import emb_func
from few_shot_example.s2ql_examplar import examplars as sql_examplars
from config.config_parse import (TEXT2DSLAGENT_COLLECTION_NAME, TEXT2DSLAGENTACT_COLLECTION_NAME,
TEXT2DSL_EXAMPLE_NUM, TEXT2DSL_FEWSHOTS_NUM, TEXT2DSL_SELF_CONSISTENCY_NUM,
ACT_MIN_WINDOWN_SIZE, ACT_MAX_WINDOWN_SIZE)
text2dsl_agent_collection = chromadb_client.get_or_create_collection(name=TEXT2DSLAGENT_COLLECTION_NAME,
embedding_function=emb_func,
metadata={"hnsw:space": "cosine"})
text2dsl_agent_act_collection = chromadb_client.get_or_create_collection(name=TEXT2DSLAGENTACT_COLLECTION_NAME,
embedding_function=emb_func,
metadata={"hnsw:space": "cosine"})
text2dsl_agent_example_prompter = FewShotPromptTemplate2(collection=text2dsl_agent_collection,
retrieval_key="question",
few_shot_seperator='\n\n')
text2dsl_agent_act_example_prompter = FewShotPromptTemplate2(collection=text2dsl_agent_act_collection,
retrieval_key="question",
few_shot_seperator='\n\n')
text2sql_agent = Text2DSLAgent(num_fewshots=TEXT2DSL_FEWSHOTS_NUM, num_examples=TEXT2DSL_EXAMPLE_NUM, num_self_consistency=TEXT2DSL_SELF_CONSISTENCY_NUM,
sql_example_prompter=text2dsl_agent_example_prompter, llm=llm)
text2sql_agent_autoCoT = Text2DSLAgentAutoCoT(num_fewshots=TEXT2DSL_FEWSHOTS_NUM, num_examples=TEXT2DSL_EXAMPLE_NUM, num_self_consistency=TEXT2DSL_SELF_CONSISTENCY_NUM,
sql_example_prompter=text2dsl_agent_act_example_prompter, llm=llm,
auto_cot_min_window_size=ACT_MIN_WINDOWN_SIZE, auto_cot_max_window_size=ACT_MAX_WINDOWN_SIZE)
sql_ids = [str(i) for i in range(0, len(sql_examplars))]
text2sql_agent.reload_setting(sql_ids, sql_examplars, TEXT2DSL_EXAMPLE_NUM, TEXT2DSL_FEWSHOTS_NUM, TEXT2DSL_SELF_CONSISTENCY_NUM)
if text2sql_agent_autoCoT.count_examples()==0:
source_dir_path = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
example_dir_path = os.path.join(source_dir_path, 'few_shot_example')
example_json_file = os.path.join(example_dir_path, 's2ql_examplar3_transformed.json')
with open(example_json_file, 'r') as f:
transformed_sql_examplar_list = json.load(f)
transformed_sql_examplar_ids = [str(i) for i in range(0, len(transformed_sql_examplar_list))]
text2sql_agent_autoCoT.reload_setting_autoCoT(transformed_sql_examplar_ids, transformed_sql_examplar_list, TEXT2DSL_EXAMPLE_NUM, TEXT2DSL_FEWSHOTS_NUM, TEXT2DSL_SELF_CONSISTENCY_NUM)
text2sql_agent_router = Text2DSLAgentWrapper(sql_agent_act=text2sql_agent_autoCoT)