diff --git a/README.md b/README.md index f176c1b9..66f94673 100644 --- a/README.md +++ b/README.md @@ -4,7 +4,7 @@

Python Version - PyPI Version + PyPI Version License GitHub Stars

@@ -28,7 +28,7 @@ Personal memory helps "**understand user preferences**", task memory helps agent ## 📰 Latest Updates -- **[2025-10]** 🚀 ReMe v0.1.10.3 released! Core enhancement: direct Python import support. You can now use ReMe without starting an HTTP or MCP service - simply `from reme_ai import ReMeApp` and call methods directly in your Python code. +- **[2025-10]** 🚀 ReMe v0.1.10.4 released! Core enhancement: direct Python import support. You can now use ReMe without starting an HTTP or MCP service - simply `from reme_ai import ReMeApp` and call methods directly in your Python code. - **[2025-10]** 🔧 Tool Memory support is now available! Enables data-driven tool selection and parameter optimization through historical performance tracking. Check out the [Tool Memory Guide](docs/tool_memory/tool_memory.md) and [benchmark results](docs/tool_memory/tool_bench.md). - **[2025-09]** 🎉 ReMe v0.1.9 has been officially released, adding support for asynchronous operations. It has also been integrated into the memory service of agentscope-runtime. diff --git a/docs/index.md b/docs/index.md index 54e7ede0..6d36da4e 100644 --- a/docs/index.md +++ b/docs/index.md @@ -17,7 +17,7 @@ kernelspec:
Python Version - PyPI Version + PyPI Version License GitHub Stars
diff --git a/docs/vector_store_api_guide.md b/docs/vector_store_api_guide.md index 83e4e194..394175a5 100644 --- a/docs/vector_store_api_guide.md +++ b/docs/vector_store_api_guide.md @@ -12,7 +12,7 @@ kernelspec: name: python3 --- -# 🚀 Vector Store API Guide +# Vector Store API Guide This guide covers the vector store implementations available in ReMe, their APIs, and how to use them effectively. diff --git a/pyproject.toml b/pyproject.toml index 6144dbf2..81242705 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta" [project] name = "reme_ai" -version = "0.1.10.3" +version = "0.1.10.4" description = "Remember me" authors = [ { name = "jinli.yl", email = "jinli.yl@alibaba-inc.com" }, @@ -24,7 +24,7 @@ classifiers = [ keywords = ["llm", "memory", "experience", "memoryscope", "ai", "mcp", "http"] dependencies = [ - "flowllm[reme]>=0.1.11.3", + "flowllm[reme]>=0.1.11.4", ] [project.optional-dependencies] diff --git a/reme_ai/__init__.py b/reme_ai/__init__.py index 6b09428d..ceac9451 100644 --- a/reme_ai/__init__.py +++ b/reme_ai/__init__.py @@ -2,7 +2,7 @@ import os os.environ["FLOW_APP_NAME"] = "ReMe" -__version__ = "0.1.10.3" +__version__ = "0.1.10.4" from reme_ai.app import ReMeApp from . import agent diff --git a/reme_ai/app.py b/reme_ai/app.py index cded3e8b..62692378 100644 --- a/reme_ai/app.py +++ b/reme_ai/app.py @@ -28,12 +28,12 @@ class ReMeApp(FlowLLMApp): """ def __init__(self, + *args, llm_api_key: str = None, llm_api_base: str = None, embedding_api_key: str = None, embedding_api_base: str = None, config_path: str = None, - *args, **kwargs): """ Initialize ReMeApp with configuration for LLM, embeddings, and vector stores. @@ -59,6 +59,29 @@ class ReMeApp(FlowLLMApp): Both approaches accept the same configuration parameters and produce identical results. Args: + *args: Additional command-line style arguments passed to parser. + These parameters are identical to the command-line startup parameters in README. + + Common configuration examples: + For complete configuration reference, see: reme_ai/config/default.yaml + + LLM Configuration: + - "llm.default.model_name=qwen3-30b-a3b-thinking-2507" - Set LLM model + - "llm.default.backend=openai_compatible" - Set LLM backend type + - "llm.default.params={'temperature': '0.6'}" - Set model parameters + + Embedding Configuration: + - "embedding_model.default.model_name=text-embedding-v4" - Set embedding model + - "embedding_model.default.backend=openai_compatible" - Set embedding backend + - "embedding_model.default.params={'dimensions': 1024}" - Embedding parameters + + Vector Store Configuration: + - "vector_store.default.backend=local" - Use local vector store + - "vector_store.default.backend=memory" - Use memory vector store + - "vector_store.default.backend=qdrant" - Use Qdrant vector store + - "vector_store.default.backend=elasticsearch" - Use Elasticsearch + - "vector_store.default.embedding_model=default" - Link vector store to embedding model + - "vector_store.default.params={'collection_name': 'my_memories'}" - Vector store parameters llm_api_key: API key for LLM service (e.g., OpenAI, Claude). If provided, this will override the FLOW_LLM_API_KEY environment variable. Environment variable: FLOW_LLM_API_KEY @@ -76,30 +99,6 @@ class ReMeApp(FlowLLMApp): config_path: Path to custom configuration YAML file. If provided, loads configuration from this file. Example: "path/to/my_config.yaml" This overrides the default configuration with your custom settings. - *args: Additional command-line style arguments passed to parser. - These parameters are identical to the command-line startup parameters in README. - - Common configuration examples: - For complete configuration reference, see: reme_ai/config/default.yaml - - LLM Configuration: - - "llm.default.model_name=qwen3-30b-a3b-thinking-2507" - Set LLM model - - "llm.default.backend=openai_compatible" - Set LLM backend type - - "llm.default.params={'temperature': '0.6'}" - Set model parameters - - Embedding Configuration: - - "embedding_model.default.model_name=text-embedding-v4" - Set embedding model - - "embedding_model.default.backend=openai_compatible" - Set embedding backend - - "embedding_model.default.params={'dimensions': 1024}" - Embedding parameters - - Vector Store Configuration: - - "vector_store.default.backend=local" - Use local vector store - - "vector_store.default.backend=memory" - Use memory vector store - - "vector_store.default.backend=qdrant" - Use Qdrant vector store - - "vector_store.default.backend=elasticsearch" - Use Elasticsearch - - "vector_store.default.embedding_model=default" - Link vector store to embedding model - - "vector_store.default.params={'collection_name': 'my_memories'}" - Vector store parameters - **kwargs: Additional keyword arguments passed to parser. Same format as args but as key-value pairs. Example: model_name="gpt-4", temperature=0.7 @@ -118,7 +117,8 @@ class ReMeApp(FlowLLMApp): - README.md "Environment Configuration" for environment variable setup - example.env for all available environment variables """ - super().__init__(llm_api_key=llm_api_key, + super().__init__(*args, + llm_api_key=llm_api_key, llm_api_base=llm_api_base, embedding_api_key=embedding_api_key, embedding_api_base=embedding_api_base, @@ -126,7 +126,6 @@ class ReMeApp(FlowLLMApp): parser=ConfigParser, config_path=config_path, load_default_config=True, - args=args, **kwargs) async def async_execute(self, name: str, **kwargs) -> dict: