Examples: query, "exact match", wildcard*, wild?ard, wild*rd
Fuzzy search: cake~ (finds cakes, bake)
Term boost: "red velvet"^4, chocolate^2
Field grouping: tags:(+work -"fun-stuff")
Escaping: Escape characters +-&|!(){}[]^"~*?:\ with \, e.g. \+
Range search: properties.timestamp:[1587729413488 TO *] (inclusive), properties.title:{A TO Z}(excluding A and Z)
Combinations: chocolate AND vanilla, chocolate OR vanilla, (chocolate OR vanilla) NOT "vanilla pudding"
Field search: properties.title:"The Title" AND text
Hello All , Good Morning ! Can You Help Better Understand The Distinction Of Cleargpt? How Is It Different From Chatgpt And What Gpt Model Are We Using In Clearml ? Thank You In Advance !

Hello All ,
Good morning !
can you help better understand the distinction of clearGPT? how is it different from chatgpt and what gpt model are we using in clearML ? Thank you in advance !

Posted one month ago
Votes Newest

Answers 5

Hi @<1628565287957696512:profile|AloofBat92>
Yeah the name is confusing, we should probably change that. The idea is it is a low code / high code , train your own LLM and deploy it. Not really chatgpt 1:1 comparison, more like, GenAI for enterprises. make sense ?

Posted one month ago

Totally understandable , but chatgpt api is not open source and also I wanted to understand a few .
How come we support the claim that there is a data leakage by using chatgpt model and how are we resolving it here with a different architecture .
Even if the architecture is different , still it is a chatgpt interface correct ? Please advise

Posted one month ago

Thank you Martin for your prompt response , meaning we can deploy any gpt models like llama2 , falcon , chatgpt , right ? I wanted to make sure the platform supports all the llm models . Please advise

Posted one month ago

That is correct. Unfortunately though this is not part of the open source, this means that for the open source it might be a bit more hands-on to deploy an llm model

Posted one month ago

still it is a chatgpt interface correct ?

Actually, no. And we will change the wording on the website so it is more intuitive to understand.
The idea is you actually train your own model (not chatgpt/openai) and use that model internally, which means everything is done inside your organisation, from data through training and ending with deployment. Does that make sense ?

Posted one month ago
5 Answers
one month ago
one month ago