decompose class hierarchy of LLM implementations #397
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@raulraja For the moment, I feel like the PR is ready for first feedback. |
|
Since this is quite a large PR, it would be good if we could get a walk-through tomorrow or early this week to see the most relevant aspects and things you changed together. |
raulraja
reviewed
Sep 20, 2023
core/src/commonTest/kotlin/com/xebia/functional/xef/conversation/ConversationSpec.kt
Outdated
Show resolved
Hide resolved
raulraja
reviewed
Sep 20, 2023
openai/src/commonMain/kotlin/com/xebia/functional/xef/conversation/llm/openai/AutoClose.kt
Show resolved
Hide resolved
raulraja
reviewed
Sep 20, 2023
openai/src/commonMain/kotlin/com/xebia/functional/xef/conversation/llm/openai/OpenAI.kt
Show resolved
Hide resolved
raulraja
previously approved these changes
Sep 20, 2023
tokenizer/src/commonMain/kotlin/com/xebia/functional/tokenizer/ModelType.kt
Show resolved
Hide resolved
javipacheco
requested changes
Sep 20, 2023
core/src/commonMain/kotlin/com/xebia/functional/xef/llm/MemoryManagement.kt
Outdated
Show resolved
Hide resolved
core/src/commonMain/kotlin/com/xebia/functional/xef/llm/MemoryManagement.kt
Outdated
Show resolved
Hide resolved
.../commonMain/kotlin/com/xebia/functional/xef/llm/models/functions/FunChatCompletionRequest.kt
Show resolved
Hide resolved
core/src/commonTest/kotlin/com/xebia/functional/xef/conversation/ConversationSpec.kt
Outdated
Show resolved
Hide resolved
openai/src/commonMain/kotlin/com/xebia/functional/xef/conversation/llm/openai/Conversions.kt
Show resolved
Hide resolved
* storing full prompt and response messages * updated the rest of the functions * fixed problem in messages order and added tests
|
PR ready, quillos? |
Montagon
approved these changes
Sep 22, 2023
Intex32
deleted the
393-decompose-class-hierarchy-of-llm-implementations
branch
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
decompose class hierarchy of LLM implementations:
from one class per provider → one class per model and it's respective capabilities
Current problem:
you may call functions on a model that the model does not support, as there is only one class per provider that all models use
in particular, ChatWithFunctions extends Chat, whereby ChatWithFunctions is not necessarily compatible with Chat, thus modelled incorrectly which can lead to unsupported operations at runtime