Home

Awesome

Multilspy: LSP client library in Python to build applications around language servers

Introduction

This repository hosts multilspy, a library developed as part of research conducted for NeruIPS 2023 paper titled "Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context" ("Guiding Language Models of Code with Global Context using Monitors" on Arxiv). The paper introduces Monitor-Guided Decoding (MGD) for code generation using Language Models, where a monitor uses static analysis to guide the decoding, ensuring that the generated code follows various correctness properties, like absence of hallucinated symbol names, valid order of method calls, etc. For further details about Monitor-Guided Decoding, please refer to the paper and GitHub repository microsoft/monitors4codegen.

multilspy is a cross-platform library designed to simplify the process of creating language server clients to query and obtain results of various static analyses from a wide variety of language servers that communicate over the Language Server Protocol. It is easily extensible to support any language that has a Language Server and currently supports Java, Rust, C# and Python. We aim to continuously add support for more language servers and languages.

Language servers are tools that perform a variety of static analyses on code repositories and provide useful information such as type-directed code completion suggestions, symbol definition locations, symbol references, etc., over the Language Server Protocol (LSP). Since LSP is language-agnostic, multilspy can provide the results for static analyses of code in different languages over a common interface.

multilspy intends to ease the process of using language servers, by handling various steps in using a language server:

Some of the analyses results that multilspy can provide are:

Installation

It is ideal to create a new virtual environment with python>=3.10. To create a virtual environment using conda and activate it:

conda create -n multilspy_env python=3.10
conda activate multilspy_env

Further details and instructions on creation of python virtual environments can be found in the official documentation. Further, we also refer users to Miniconda, as an alternative to the above steps for creation of the virtual environment.

To install multilspy using pip, execute the following command:

pip install https://github.com/microsoft/multilspy/archive/main.zip

Usage

Example usage:

from multilspy import SyncLanguageServer
from multilspy.multilspy_config import MultilspyConfig
from multilspy.multilspy_logger import MultilspyLogger
...
config = MultilspyConfig.from_dict({"code_language": "java"}) # Also supports "python", "rust", "csharp"
logger = MultilspyLogger()
lsp = SyncLanguageServer.create(config, logger, "/abs/path/to/project/root/")
with lsp.start_server():
    result = lsp.request_definition(
        "relative/path/to/code_file.java", # Filename of location where request is being made
        163, # line number of symbol for which request is being made
        4 # column number of symbol for which request is being made
    )
    result2 = lsp.request_completions(
        ...
    )
    result3 = lsp.request_references(
        ...
    )
    result4 = lsp.request_document_symbols(
        ...
    )
    result5 = lsp.request_hover(
        ...
    )
    ...

multilspy also provides an asyncio based API which can be used in async contexts. Example usage (asyncio):

from multilspy import LanguageServer
...
lsp = LanguageServer.create(...)
async with lsp.start_server():
    result = await lsp.request_definition(
        ...
    )
    ...

The file src/multilspy/language_server.py provides the multilspy API. Several tests for multilspy present under tests/multilspy/ provide detailed usage examples for multilspy. The tests can be executed by running:

pytest tests/multilspy

Use of multilspy in AI4Code Scenarios like Monitor-Guided Decoding

multilspy provides all the features that language-server-protocol provides to IDEs like VSCode. It is useful to develop toolsets that can interface with AI systems like Large Language Models (LLM). One such usecase is Monitor-Guided Decoding, where multilspy is used to find results of static analyses like type-directed completions, to guide the token-by-token generation of code using an LLM, ensuring that all generated identifier/method names are valid in the context of the repository, significantly boosting the compilability of generated code. MGD also demonstrates use of multilspy to create monitors that ensure all function calls in LLM generated code receive correct number of arguments, and that functions of an object are called in the right order following a protocol (like not calling "read" before "open" on a file object).

Frequently Asked Questions (FAQ)

asyncio related Runtime error when executing the tests for MGD

If you get the following error:

RuntimeError: Task <Task pending name='Task-2' coro=<_AsyncGeneratorContextManager.__aenter__() running at
    python3.8/contextlib.py:171> cb=[_chain_future.<locals>._call_set_state() at
    python3.8/asyncio/futures.py:367]> got Future <Future pending> attached to a different loop python3.8/asyncio/locks.py:309: RuntimeError

Please ensure that you create a new environment with Python >=3.10. For further details, please have a look at the StackOverflow Discussion.

Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.