Merge branch 'fixbug/v0.6-release' into geekan/main

This commit is contained in:
莘权 马 2024-01-04 13:54:27 +08:00
commit 1b06d933b2
5 changed files with 17 additions and 6 deletions

View file

@ -34,7 +34,10 @@ # MetaGPT: The Multi-Agent Framework
<p align="center">Software Company Multi-Role Schematic (Gradually Implementing)</p>
## News
- Dec 15: [v0.5.0](https://github.com/geekan/MetaGPT/releases/tag/v0.5.0) is released! We introduce **incremental development**, facilitating agents to build up larger projects on top of their previous efforts or existing codebase. We also launch a whole collection of important features, including **multilingual support** (experimental), multiple **programming languages support** (experimental), **incremental development** (experimental), CLI support, pip support, enhanced code review, documentation mechanism, and optimized messaging mechanism!
🚀 Jan 03: Here comes [v0.6.0](https://github.com/geekan/MetaGPT/releases/tag/v0.6.0)! In this version, we added serialization and deserialization of important objects and enabled breakpoint recovery. We upgraded OpenAI package to v1.6.0 and supported Gemini, ZhipuAI, Ollama, OpenLLM, etc. Moreover, we provided extremely simple examples where you need only 7 lines to implement a general election [debate](https://github.com/geekan/MetaGPT/blob/main/examples/debate_simple.py). Check out more details [here](https://github.com/geekan/MetaGPT/releases/tag/v0.6.0)!
🚀 Dec 15: [v0.5.0](https://github.com/geekan/MetaGPT/releases/tag/v0.5.0) is released! We introduced **incremental development**, facilitating agents to build up larger projects on top of their previous efforts or existing codebase. We also launched a whole collection of important features, including **multilingual support** (experimental), multiple **programming languages support** (experimental), **incremental development** (experimental), CLI support, pip support, enhanced code review, documentation mechanism, and optimized messaging mechanism!
## Install

View file

@ -15,6 +15,7 @@ OPENAI_API_MODEL: "gpt-4-1106-preview"
MAX_TOKENS: 4096
RPM: 10
TIMEOUT: 60 # Timeout for llm invocation
#DEFAULT_PROVIDER: openai
#### if Spark
#SPARK_APPID : "YOUR_APPID"

View file

@ -50,6 +50,9 @@ class LLMProviderEnum(Enum):
AZURE_OPENAI = "azure_openai"
OLLAMA = "ollama"
def __missing__(self, key):
return self.OPENAI
class Config(metaclass=Singleton):
"""
@ -108,6 +111,11 @@ class Config(metaclass=Singleton):
if v:
provider = k
break
if provider is None:
if self.DEFAULT_PROVIDER:
provider = LLMProviderEnum(self.DEFAULT_PROVIDER)
else:
raise NotConfiguredException("You should config a LLM configuration first")
if provider is LLMProviderEnum.GEMINI and not require_python_version(req_version=(3, 10)):
warnings.warn("Use Gemini requires Python >= 3.10")
@ -117,7 +125,6 @@ class Config(metaclass=Singleton):
if provider:
logger.info(f"API: {provider}")
return provider
raise NotConfiguredException("You should config a LLM configuration first")
def get_model_name(self, provider=None) -> str:
provider = provider or self.get_default_llm_provider_enum()

View file

@ -22,7 +22,7 @@ pandas==2.0.3
pydantic==2.5.3
#pygame==2.1.3
#pymilvus==2.2.8
pytest==7.2.2
# pytest==7.2.2 # test extras require
python_docx==0.8.11
PyYAML==6.0.1
# sentence_transformers==2.2.2
@ -38,7 +38,7 @@ typing-inspect==0.8.0
typing_extensions==4.9.0
libcst==1.0.1
qdrant-client==1.7.0
pytest-mock==3.11.1
# pytest-mock==3.11.1 # test extras require
# open-interpreter==0.1.7; python_version>"3.9" # Conflict with openai 1.x
ta==0.10.2
semantic-kernel==0.4.3.dev0
@ -57,5 +57,5 @@ gitignore-parser==0.1.9
websockets~=12.0
networkx~=3.2.1
google-generativeai==0.3.2
playwright==1.40.0
# playwright==1.40.0 # playwright extras require
anytree

View file

@ -56,7 +56,7 @@ extras_require["dev"] = (["pylint~=3.0.3", "black~=23.3.0", "isort~=5.12.0", "pr
setup(
name="metagpt",
version="0.5.2",
version="0.6.0",
description="The Multi-Agent Framework",
long_description=long_description,
long_description_content_type="text/markdown",