tomtan
c173fa45a7
- Implement HermesClient for interacting with the Hermes CLI. - Create judge module for grading QA outputs from Hermes memory. - Develop LoCoMo dataset parsing and formatting utilities. - Introduce run_eval script to facilitate memory evaluation using LoCoMo-style datasets.
26 lines
673 B
YAML
26 lines
673 B
YAML
hermes:
|
||
command: "hermes"
|
||
timeout_seconds: 600
|
||
quiet: true
|
||
source: "memory-eval"
|
||
extra_args: []
|
||
|
||
memory:
|
||
env_file: "/home/tom/.hermes/memory_system.env"
|
||
endpoint: "http://127.0.0.1:1934"
|
||
api_key: ""
|
||
user_prefix: "locomo-"
|
||
search_use_llm: false
|
||
commit_every_turns: 1
|
||
commit_interval_seconds: 0
|
||
|
||
qa:
|
||
prompt_template: "请先使用 memory_system_search 查询长期记忆，再根据检索到的记忆回答问题。如果记忆中没有答案，请直接说不知道，不要编造。\n\n问题：{question}"
|
||
|
||
judge:
|
||
base_url: "https://api.openai.com/v1"
|
||
api_key_env: "OPENAI_API_KEY"
|
||
model: "gpt-4o-mini"
|
||
parallel: 4
|
||
timeout_seconds: 120
|