update requirement,Dockerfile

Author: pursues

docker/.env.example

@@ -3,32 +3,31 @@
 
 ## Base
 TZ=Asia/Shanghai
-ENV_NAME=PLAYGROUND_OFFLINE                 # Tag shown in DingTalk notifications (e.g., PROD_ONLINE/TEST); no runtime effect unless ENABLE_DINGDING_BOT=true
 MOS_CUBE_PATH=/tmp/data_test               # local data path
 MEMOS_BASE_PATH=.                          # CLI/SDK cache path
 MOS_ENABLE_DEFAULT_CUBE_CONFIG=true        # enable default cube config
 MOS_ENABLE_REORGANIZE=false                # enable memory reorg
+# MOS Text Memory Type
 MOS_TEXT_MEM_TYPE=general_text             # general_text | tree_text
 ASYNC_MODE=sync                            # async/sync, used in default cube config
 
 ## User/session defaults
-MOS_USER_ID=root
-MOS_SESSION_ID=default_session
-MOS_MAX_TURNS_WINDOW=20
+# Top-K for LLM in the Product API（old version）
 MOS_TOP_K=50
 
 ## Chat LLM (main dialogue)
+# LLM model name for the Product API
 MOS_CHAT_MODEL=gpt-4o-mini
+# Temperature for LLM in the Product API
 MOS_CHAT_TEMPERATURE=0.8
-MOS_MAX_TOKENS=8000
+# Max tokens for LLM in the Product API
+MOS_MAX_TOKENS=2048
+# Top-P for LLM in the Product API
 MOS_TOP_P=0.9
+# LLM for the Product API backend
 MOS_CHAT_MODEL_PROVIDER=openai             # openai | huggingface | vllm
-MOS_MODEL_SCHEMA=memos.configs.llm.VLLMLLMConfig  # vllm only: config class path; keep default unless you extend it
 OPENAI_API_KEY=sk-xxx                      # [required] when provider=openai
 OPENAI_API_BASE=https://api.openai.com/v1  # [required] base for the key
-OPENAI_BASE_URL=                           # compatibility for eval/scheduler
-VLLM_API_KEY=                              # required when provider=vllm
-VLLM_API_BASE=http://localhost:8088/v1     # required when provider=vllm
 
 ## MemReader / retrieval LLM
 MEMRADER_MODEL=gpt-4o-mini
@@ -37,31 +36,60 @@ MEMRADER_API_BASE=http://localhost:3000/v1 # [required] base for the key
 MEMRADER_MAX_TOKENS=5000
 
 ## Embedding & rerank
+# embedding dim
 EMBEDDING_DIMENSION=1024
+# set default embedding backend
 MOS_EMBEDDER_BACKEND=universal_api        # universal_api | ollama
+# set openai style
 MOS_EMBEDDER_PROVIDER=openai              # required when universal_api
+# embedding model
 MOS_EMBEDDER_MODEL=bge-m3                 # siliconflow → use BAAI/bge-m3
+# embedding url
 MOS_EMBEDDER_API_BASE=http://localhost:8000/v1 # required when universal_api
+# embedding model key
 MOS_EMBEDDER_API_KEY=EMPTY                 # required when universal_api
 OLLAMA_API_BASE=http://localhost:11434     # required when backend=ollama
+# reanker config
 MOS_RERANKER_BACKEND=http_bge             # http_bge | http_bge_strategy | cosine_local
+# reanker url
 MOS_RERANKER_URL=http://localhost:8001     # required when backend=http_bge*
+# reranker model
 MOS_RERANKER_MODEL=bge-reranker-v2-m3     # siliconflow → use BAAI/bge-reranker-v2-m3
 MOS_RERANKER_HEADERS_EXTRA=               # extra headers, JSON string, e.g. {"Authorization":"Bearer your_token"}
+# use source
 MOS_RERANKER_STRATEGY=single_turn
-MOS_RERANK_SOURCE=                        # optional rerank scope, e.g., history/stream/custom
+
+
+# External Services (for evaluation scripts)
+# API key for reproducting Zep(compertitor product)  evaluation
+ZEP_API_KEY=your_zep_api_key_here
+# API key for reproducting Mem0(compertitor product)  evaluation
+MEM0_API_KEY=your_mem0_api_key_here
+# API key for reproducting MemU(compertitor product)  evaluation
+MEMU_API_KEY=your_memu_api_key_here
+# API key for reproducting MEMOBASE(compertitor product)  evaluation
+MEMOBASE_API_KEY=your_memobase_api_key_here
+# Project url for reproducting MEMOBASE(compertitor product)  evaluation
+MEMOBASE_PROJECT_URL=your_memobase_project_url_here
+# LLM for evaluation
+MODEL=gpt-4o-mini
+# embedding model for evaluation
+EMBEDDING_MODEL=nomic-embed-text:latest
 
 ## Internet search & preference memory
+# Enable web search
 ENABLE_INTERNET=false
+# API key for BOCHA Search
 BOCHA_API_KEY=                             # required if ENABLE_INTERNET=true
+# default search mode
 SEARCH_MODE=fast                          # fast | fine | mixture
-FAST_GRAPH=false
-BM25_CALL=false
-VEC_COT_CALL=false
+# Slow retrieval strategy configuration, rewrite is the rewrite strategy
 FINE_STRATEGY=rewrite                     # rewrite | recreate | deep_search
-ENABLE_ACTIVATION_MEMORY=false
+# Whether to enable preference memory
 ENABLE_PREFERENCE_MEMORY=true
+# Preference Memory Add Mode
 PREFERENCE_ADDER_MODE=fast                # fast | safe
+# Whether to deduplicate explicit preferences based on factual memory
 DEDUP_PREF_EXP_BY_TEXTUAL=false
 
 ## Reader chunking
@@ -72,101 +100,115 @@ MEM_READER_CHAT_CHUNK_SESS_SIZE=10         # sessions per chunk (default mode)
 MEM_READER_CHAT_CHUNK_OVERLAP=2            # overlap between chunks
 
 ## Scheduler (MemScheduler / API)
+# Enable or disable the main switch for configuring the memory scheduler during MemOS class initialization
 MOS_ENABLE_SCHEDULER=false
+# Determine the number of most relevant memory entries that the scheduler retrieves or processes during runtime (such as reordering or updating working memory)
 MOS_SCHEDULER_TOP_K=10
+# The time interval (in seconds) for updating "Activation Memory" (usually referring to caching or short-term memory mechanisms)
 MOS_SCHEDULER_ACT_MEM_UPDATE_INTERVAL=300
+# The size of the context window considered by the scheduler when processing tasks (such as the number of recent messages or conversation rounds)
 MOS_SCHEDULER_CONTEXT_WINDOW_SIZE=5
+# The maximum number of working threads allowed in the scheduler thread pool for concurrent task execution
 MOS_SCHEDULER_THREAD_POOL_MAX_WORKERS=10000
+# The polling interval (in seconds) for the scheduler to consume new messages/tasks from the queue. The smaller the value, the faster the response, but the CPU usage may be higher
 MOS_SCHEDULER_CONSUME_INTERVAL_SECONDS=0.01
+# Whether to enable the parallel distribution function of the scheduler to improve the throughput of concurrent operations
 MOS_SCHEDULER_ENABLE_PARALLEL_DISPATCH=true
+# The specific switch to enable or disable the "Activate Memory" function in the scheduler logic
 MOS_SCHEDULER_ENABLE_ACTIVATION_MEMORY=false
+# Control whether the scheduler instance is actually started during server initialization. If false, the scheduler object may be created but its background loop will not be started
 API_SCHEDULER_ON=true
+# Specifically define the window size for API search operations in OptimizedScheduler. It is passed to the ScherderrAPIModule to control the scope of the search context
 API_SEARCH_WINDOW_SIZE=5
+# Specify how many rounds of previous conversations (history) to retrieve and consider during the 'hybrid search' (fast search+asynchronous fine search). This helps provide context aware search results
 API_SEARCH_HISTORY_TURNS=5
 
 ## Graph / vector stores
+# Neo4j database selection mode
 NEO4J_BACKEND=neo4j-community             # neo4j-community | neo4j | nebular | polardb
+# Neo4j database url
 NEO4J_URI=bolt://localhost:7687           # required when backend=neo4j*
+#  Neo4j database user
 NEO4J_USER=neo4j                          # required when backend=neo4j*
+# Neo4j database password
 NEO4J_PASSWORD=12345678                   # required when backend=neo4j*
+# Neo4j database name
 NEO4J_DB_NAME=neo4j                       # required for shared-db mode
+# Neo4j database data sharing with Memos
 MOS_NEO4J_SHARED_DB=false
 QDRANT_HOST=localhost
 QDRANT_PORT=6333
 # For Qdrant Cloud / remote endpoint (takes priority if set):
 QDRANT_URL=your_qdrant_url
 QDRANT_API_KEY=your_qdrant_key
+# milvus server uri
 MILVUS_URI=http://localhost:19530         # required when ENABLE_PREFERENCE_MEMORY=true
 MILVUS_USER_NAME=root                     # same as above
 MILVUS_PASSWORD=12345678                  # same as above
-NEBULAR_HOSTS=["localhost"]
-NEBULAR_USER=root
-NEBULAR_PASSWORD=xxxxxx
-NEBULAR_SPACE=shared-tree-textual-memory
-NEBULAR_WORKING_MEMORY=20
-NEBULAR_LONGTERM_MEMORY=1000000
-NEBULAR_USER_MEMORY=1000000
-
-## Relational DB (user manager / PolarDB)
-MOS_USER_MANAGER_BACKEND=sqlite           # sqlite | mysql
-MYSQL_HOST=localhost                      # required when backend=mysql
-MYSQL_PORT=3306
-MYSQL_USERNAME=root
-MYSQL_PASSWORD=12345678
-MYSQL_DATABASE=memos_users
-MYSQL_CHARSET=utf8mb4
+
+# PolarDB endpoint/host
 POLAR_DB_HOST=localhost
+# PolarDB port
 POLAR_DB_PORT=5432
+# PolarDB username
 POLAR_DB_USER=root
+# PolarDB password
 POLAR_DB_PASSWORD=123456
+# PolarDB database name
 POLAR_DB_DB_NAME=shared_memos_db
+# PolarDB Server Mode:
+# If set to true, use Multi-Database Mode where each user has their own independent database (physical isolation).
+# If set to false (default), use Shared Database Mode where all users share one database with logical isolation via username.
 POLAR_DB_USE_MULTI_DB=false
+# PolarDB connection pool size
+POLARDB_POOL_MAX_CONN=100
 
-## Redis (scheduler queue) — fill only if you want scheduler queues in Redis; otherwise in-memory queue is used
-REDIS_HOST=localhost                      # global Redis endpoint (preferred over MEMSCHEDULER_*)
-REDIS_PORT=6379
-REDIS_DB=0
-REDIS_PASSWORD=
-REDIS_SOCKET_TIMEOUT=
-REDIS_SOCKET_CONNECT_TIMEOUT=
+## Related configurations of Redis
+# Reddimq sends scheduling information and synchronization information for some variables
 MEMSCHEDULER_REDIS_HOST=                  # fallback keys if not using the global ones
 MEMSCHEDULER_REDIS_PORT=
 MEMSCHEDULER_REDIS_DB=
 MEMSCHEDULER_REDIS_PASSWORD=
 MEMSCHEDULER_REDIS_TIMEOUT=
 MEMSCHEDULER_REDIS_CONNECT_TIMEOUT=
 
-## MemScheduler LLM
-MEMSCHEDULER_OPENAI_API_KEY=              # LLM key for scheduler’s own calls (OpenAI-compatible); leave empty if scheduler not using LLM
-MEMSCHEDULER_OPENAI_BASE_URL=             # Base URL for the above; can reuse OPENAI_API_BASE
-MEMSCHEDULER_OPENAI_DEFAULT_MODEL=gpt-4o-mini
 
 ## Nacos (optional config center)
+# Nacos turns off long polling listening, defaults to true
 NACOS_ENABLE_WATCH=false
+# The monitoring interval for long rotation training is 60 seconds, and the default 30 seconds can be left unconfigured
 NACOS_WATCH_INTERVAL=60
+# nacos server address
 NACOS_SERVER_ADDR=
+# nacos dataid
 NACOS_DATA_ID=
+# nacos group
 NACOS_GROUP=DEFAULT_GROUP
+# nacos namespace
 NACOS_NAMESPACE=
+# nacos ak
 AK=
+# nacos sk
 SK=
 
-## DingTalk bot & OSS upload
-ENABLE_DINGDING_BOT=false                 # set true -> fields below required
-DINGDING_ACCESS_TOKEN_USER=
-DINGDING_SECRET_USER=
-DINGDING_ACCESS_TOKEN_ERROR=
-DINGDING_SECRET_ERROR=
-DINGDING_ROBOT_CODE=
-DINGDING_APP_KEY=
-DINGDING_APP_SECRET=
-OSS_ENDPOINT=                             # bot image upload depends on OSS
-OSS_REGION=
-OSS_BUCKET_NAME=
-OSS_ACCESS_KEY_ID=
-OSS_ACCESS_KEY_SECRET=
-OSS_PUBLIC_BASE_URL=
-
-## SDK / external client
-MEMOS_API_KEY=
-MEMOS_BASE_URL=https://memos.memtensor.cn/api/openmem/v1
+# chat model for chat api
+CHAT_MODEL_LIST='[{
+  "backend": "deepseek",
+  "api_base": "http://localhost:1234",
+  "api_key": "your-api-key",
+  "model_name_or_path": "deepseek-r1",
+  "support_models": ["deepseek-r1"]
+}]'
+
+# RabbitMQ host name for message-log pipeline
+MEMSCHEDULER_RABBITMQ_HOST_NAME=
+# RabbitMQ user name for message-log pipeline
+MEMSCHEDULER_RABBITMQ_USER_NAME=
+# RabbitMQ password for message-log pipeline
+MEMSCHEDULER_RABBITMQ_PASSWORD=
+# RabbitMQ virtual host for message-log pipeline
+MEMSCHEDULER_RABBITMQ_VIRTUAL_HOST=memos
+# Erase connection state on connect for message-log pipeline
+MEMSCHEDULER_RABBITMQ_ERASE_ON_CONNECT=true
+# RabbitMQ port for message-log pipeline
+MEMSCHEDULER_RABBITMQ_PORT=5672

docker/Dockerfile

@@ -32,4 +32,4 @@ ENV PYTHONPATH=/app/src
 EXPOSE 8000
 
 # Start the docker
-CMD ["uvicorn", "memos.api.product_api:app", "--host", "0.0.0.0", "--port", "8000", "--reload"]
+CMD ["uvicorn", "memos.api.server_api:app", "--host", "0.0.0.0", "--port", "8000", "--reload"]