LocalAI/examples/query_data/store.py
quoing e7981152b2
[query_data example] max_chunk_overlap in PromptHelper must be in 0..1 range (#1000)
**Description**

Simple fix, percentage value is expected to be float in range 0..1

**Notes for Reviewers**


**[Signed
commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)**
- [x] Yes, I signed my commits.
 

<!--
Thank you for contributing to LocalAI! 

Contributing Conventions:

1. Include descriptive PR titles with [<component-name>] prepended.
2. Build and test your changes before submitting a PR. 
3. Sign your commits

By following the community's contribution conventions upfront, the
review process will
be accelerated and your PR merged more quickly.
-->
2023-09-04 19:12:53 +02:00

28 lines
1.2 KiB
Python

import os
# Uncomment to specify your OpenAI API key here (local testing only, not in production!), or add corresponding environment variable (recommended)
# os.environ['OPENAI_API_KEY']= ""
from llama_index import GPTVectorStoreIndex, SimpleDirectoryReader, LLMPredictor, PromptHelper, ServiceContext
from langchain.llms.openai import OpenAI
from llama_index import StorageContext, load_index_from_storage
base_path = os.environ.get('OPENAI_API_BASE', 'http://localhost:8080/v1')
# This example uses text-davinci-003 by default; feel free to change if desired
llm_predictor = LLMPredictor(llm=OpenAI(temperature=0, model_name="gpt-3.5-turbo", openai_api_base=base_path))
# Configure prompt parameters and initialise helper
max_input_size = 400
num_output = 400
max_chunk_overlap = 0.3
prompt_helper = PromptHelper(max_input_size, num_output, max_chunk_overlap)
# Load documents from the 'data' directory
documents = SimpleDirectoryReader('data').load_data()
service_context = ServiceContext.from_defaults(llm_predictor=llm_predictor, prompt_helper=prompt_helper, chunk_size_limit = 400)
index = GPTVectorStoreIndex.from_documents(documents, service_context=service_context)
index.storage_context.persist(persist_dir="./storage")