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:
- Anthropic, Azure, Mistral, OpenAI
- Vertex AI Gemini. Resolve API deprivation issue. Streamline Geminie output code. Serialise citation and safety 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 AssistantMessage fields final.
Experiment with Message and Token window chat history
Comment From: markpollack
outdated, has been taken care of in other commits. closing