[DERCBOT-1037] Use of PromptTemplate And Rewrite the RAG chain using LCEL #1772
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
assouktim
force-pushed
the
feature/dercbot-1037
branch
3 times, most recently
from
3a890f3 to
c93e056
Compare
assouktim
force-pushed
the
feature/dercbot-1037
branch
from
a76469a to
f184b16
Compare
assouktim
changed the title
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Outdated suggestions cannot be applied.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.
This pull request includes several changes to the RAG (Retrieval-Augmented Generation) system to improve prompt handling, dependency updates, and refactoring of callback handlers and utility functions. The most important changes are summarized below:
Improvements to Prompt Handling:
RAGQueryto usePromptTemplateinstead ofquestionAnsweringPromptInputsfor better prompt handling. (bot/engine/src/main/kotlin/engine/config/RAGAnswerHandler.kt,gen-ai/orchestrator-client/src/main/kotlin/ai/tock/genai/orchestratorclient/requests/RAGQuery.kt,gen-ai/orchestrator-server/src/main/python/server/src/gen_ai_orchestrator/routers/requests/requests.py) [1] [2] [3] [4] [5]Dependency Updates:
pyproject.tomlto their latest versions to ensure compatibility and security. (gen-ai/orchestrator-server/src/main/python/server/pyproject.toml) [1] [2]Refactoring and Cleanup:
validate_prompt_templatefunction fromcompletion_service.pyand moved it toprompt_utility.pyfor better modularity. (gen-ai/orchestrator-server/src/main/python/server/src/gen_ai_orchestrator/services/completion/completion_service.py) [1] [2] [3]RetrieverJsonCallbackHandlerwithRAGCallbackHandlerto improve callback handling in the RAG chain execution. (gen-ai/orchestrator-server/src/main/python/server/src/gen_ai_orchestrator/services/langchain/callbacks/rag_callback_handler.py,gen-ai/orchestrator-server/src/main/python/server/src/gen_ai_orchestrator/services/langchain/rag_chain.py) [1] [2] [3] [4] [5] [6]These changes enhance the robustness, maintainability, and performance of the RAG system.