Spaces:
Sleeping
Sleeping
| import os | |
| from typing import Optional | |
| from pydantic import Field, BaseModel | |
| from omegaconf import OmegaConf | |
| from llama_index.core.utilities.sql_wrapper import SQLDatabase | |
| from sqlalchemy import create_engine, text | |
| from dotenv import load_dotenv | |
| load_dotenv(override=True) | |
| from vectara_agentic.agent import Agent | |
| from vectara_agentic.tools import ToolsFactory, VectaraToolFactory | |
| def create_assistant_tools(cfg): | |
| class QueryCFPBComplaints(BaseModel): | |
| query: str = Field(description="The user query.") | |
| vec_factory = VectaraToolFactory(vectara_api_key=cfg.api_keys, | |
| vectara_customer_id=cfg.customer_id, | |
| vectara_corpus_id=cfg.corpus_ids) | |
| summarizer = 'vectara-experimental-summary-ext-2023-12-11-med-omni' | |
| ask_complaints = vec_factory.create_rag_tool( | |
| tool_name = "ask_complaints", | |
| tool_description = """ | |
| Given a user query, | |
| returns a response to a user question about customer complaints about bank services. | |
| """, | |
| tool_args_schema = QueryCFPBComplaints, | |
| reranker = "multilingual_reranker_v1", rerank_k = 100, | |
| n_sentences_before = 2, n_sentences_after = 2, lambda_val = 0.005, | |
| summary_num_results = 5, | |
| vectara_summarizer = summarizer, | |
| include_citations = False, | |
| ) | |
| tools_factory = ToolsFactory() | |
| db_tools = tools_factory.database_tools( | |
| tool_name_prefix = "cfpb", | |
| content_description = 'Customer complaints about five banks (Bank of America, Wells Fargo, Capital One, Chase, and CITI Bank)', | |
| sql_database = SQLDatabase(create_engine('sqlite:///cfpb_database.db')), | |
| ) | |
| return (tools_factory.standard_tools() + | |
| tools_factory.guardrail_tools() + | |
| db_tools + | |
| [ask_complaints] | |
| ) | |
| def initialize_agent(_cfg, update_func=None): | |
| cfpb_complaints_bot_instructions = """ | |
| - You are a helpful research assistant, with expertise in complaints from the Consumer Financial Protection Bureau, in conversation with a user. | |
| - Before answering any user query, use cfpb_describe_tables to understand schema of each table, and use get_sample_data | |
| to get sample data from each table in the database, so that you can understand NULL and unique values for each column. | |
| - For a query with multiple sub-questions, break down the query into the sub-questions, | |
| and make separate calls to the ask_complaints tool to answer each sub-question, | |
| then combine the answers to provide a complete response. | |
| - Use the database tools (cfpb_load_data, cfpb_describe_tables and cfpb_list_tables) to answer analytical queries. | |
| - IMPORTANT: When using database_tools, always call the ev_load_sample_data tool with the table you want to query | |
| to understand the table structure, column naming, and values in the table. Never call the cfpb_load_data tool for a query until you have called cfpb_load_sample_data. | |
| - When providing links, try to put the name of the website or source of information for the displayed text. Don't just say 'Source'. | |
| - Never discuss politics, and always respond politely. | |
| """ | |
| agent = Agent( | |
| tools=create_assistant_tools(_cfg), | |
| topic="Customer complaints from the Consumer Financial Protection Bureau (CFPB)", | |
| custom_instructions=cfpb_complaints_bot_instructions, | |
| update_func=update_func | |
| ) | |
| agent.report() | |
| return agent | |
| def get_agent_config() -> OmegaConf: | |
| cfg = OmegaConf.create({ | |
| 'customer_id': str(os.environ['VECTARA_CUSTOMER_ID']), | |
| 'corpus_ids': str(os.environ['VECTARA_CORPUS_IDS']), | |
| 'api_keys': str(os.environ['VECTARA_API_KEYS']), | |
| 'examples': os.environ.get('QUERY_EXAMPLES', None), | |
| 'demo_name': "cfpb-assistant", | |
| 'demo_welcome': "Welcome to the CFPB Customer Complaints demo.", | |
| 'demo_description': "This assistant can help you gain insights into customer complaints to banks recorded by the Consumer Financial Protection Bureau.", | |
| }) | |
| return cfg | |