Comments (2)
Sorry for the delayed reply!
-
We match experiences using the "metrics" attribute, which is saved as the index ("pg_content") in Chromadb by default.
-
The actual metric values is appended outside the experience, which are generally not exact caused by approximate matching.
![image](https://private-user-images.githubusercontent.com/17394639/339195767-44029078-6488-4348-b7ca-18dd342c2a41.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.rbNr3WbHtrPgg3OU5Reot4ns44XanEIdvhJl6S4vuMg)
from db-gpt.
Thank you for the clarification!
To ensure I understand correctly, the "metrics" attribute of an Experience is the primary component used for matching within Chroma DB. However, the actual metric values appended outside the Experience may not be exact due to approximate matching.
Could you also provide some insights on how the variables within the "desc" attribute of an Experience, such as "inserted_tuples_threshold", are handled? Are these variables dynamically evaluated by the system or the expert?
Thank you once again for your assistance.
from db-gpt.
Related Issues (20)
- 需要安装 protobuf 包 HOT 1
- running batch_main.py error HOT 1
- RuntimeError: main thread is not in main loop HOT 1
- 得到了一个空的前端页面信息 HOT 2
- How is workload_sqls obtained in main.py HOT 2
- Can i setup without prometheus? HOT 4
- running with baichung2 asks for openai error HOT 12
- Video walkthrough for setup with baichung model HOT 1
- support for mysql database
- support config for private openai proxy HOT 1
- python 3.8装不了scipy==1.11.1 SentenceTransformer默认初始化选cuda导致算相似度的时候由于设备不同弹错
- readme里写的是pg12或更高版本,但pg15 pg_stat_statements表里没有total_time ; 改成total_exec_time了吧? HOT 1
- TypeError When Using Diagnosis function. HOT 3
- Clarification on UCT(v) Implementation in Tree Search Algorithm HOT 1
- support other online models? HOT 1
- API通信遇到错误:peer closed connection without sending complete message body HOT 1
- [bug] 启动后无法对话 HOT 2
- pip install jq fails on windows HOT 1
- sync data to es error. HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from db-gpt.