[WIP] Add missing response fields to Spring AI ChatResponse, Generation and AssistantMessage #550
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
Support cha-history management at Spring AI abstraction level.
Ensure that Generation and AssistantMessage has Id, index, isCompleted attributes.
Also the ChatResponse should have an unique ID as well.
Refactor all LLM APIs to introduce the reponse ID and index and hasFinished (isCompleted) status.
Some of the APIs provide build in unique response ID and finished reason. But many does not.
For later we generate a synthetic IDs.
Add ID,index and isCompleted to the following LLM API responses:
- Anthropic, Azure, Mistral, OpenAI
- Vertex AI Gemini. Resolve API deprication issue. Streamline Geminie output code.
Serialize citation and safty output in message properties.
- Ollama support
- Bedrock cohere result metadata propagation.
- Bedrock Llama2 and Titan
- Berock Jurassic2
- Bedrock Anthropic2
- WatsanxAI
- Vertex PaLM2, HuggingFace
- Remove Generation.withGenerationMetadata
- Remove AssistantPromptTemplate
- Make all Generation field final.
- Make all AssitantMessage fields final.
Experiment with Message and Token window chat history
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Outdated suggestions cannot be applied.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.
Ensure that Generation and AssistantMessage has Id, index, isCompleted attributes.
Also the ChatResponse should have an unique ID as well.
Refactor all LLM APIs to introduce the response ID and index and hasFinished (isCompleted) status.
Some of the APIs provide build in unique response ID and finished reason. But many does not.
For later we generate a synthetic IDs.
Add ID, index and isCompleted to the following LLM API responses:
Experiment with Message and Token window chat history