Batch data save in db #1185
Open
Batch data save in db #1185
Conversation
This file contains hidden or 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
- Introduced a new JSON column `batch_data` in the `ConversationLog` model to store batch-related information. - Implemented `create_batch_conversation_logs` function to handle batch log creation for multiple messages. - Added `updateConversationLog` and `updateConversationLogByBatchData` functions for updating logs based on log ID and batch data. - Enhanced the `batch` function to process batch conversation logs in the background. - Updated the `check_batch_status` function to update conversation logs with results from batch processing. This update improves the handling of batch requests and enhances the logging mechanism for better tracking of conversation states.
harshhsahu
requested changes
Jan 17, 2026
Collaborator
harshhsahu
left a comment
harshhsahu
left a comment
There was a problem hiding this comment.
- custom id -> message_id
- webhook+response store
- improve llm msg when data in queued
- error handle data missing
- use same function
- metrix handling
…of custom_id - Renamed `custom_id` to `message_id` in various functions and services to improve clarity and consistency. - Updated the `updateConversationLogByBatchData` function to reflect the change in parameter naming. - Adjusted batch processing services (Gemini, Mistral, Anthropic, OpenAI, Groq) to use `message_id` for API requests and responses. - Enhanced the `Batch_Response_formatter` and `process_batch_results` functions to accommodate the new naming convention. - Modified the `check_batch_status` function to ensure proper handling of message_id during log updates. This update streamlines the handling of message identifiers across the codebase, improving maintainability and readability.
- Added `org_id`, `bridge_id`, `version_id`, and `thread_id` to the batch JSON payloads in Gemini, Mistral, Anthropic, OpenAI, and Groq services for improved tracking and context. - Updated the `check_batch_status` function to handle new metadata and calculate individual message costs, including metrics storage for batch processing. - Enhanced error handling and logging for metrics saving to Timescale DB. This update improves the granularity of batch processing data and facilitates better monitoring and cost calculation.
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.
No description provided.