- prompt-template takes config from the config-svc, dynamically reloads
as new config appears.
- agent-react takes config from config-svc, dynamically reloads
- Fixed lack of data in config queue, needed to take the Earliest, not the
Latest values.
- Changed text-completion and knowledge-query tool to both use 'query'
as the argument.
- Prompt and agent no longer have command line args to supply
configuration.
* - Fixed error reporting in config
- Updated tg-init-pulsar to be able to load initial config to config-svc
- Tweaked API naming and added more config calls
* Tools to dump out prompts and agent tools
Configuration service provides an API to change configuration. Complete configuration is pushed down a config queue so that users have a complete copy of config object.
Reconfigure so that AZURE_TOKEN, AZURE_MODEL and AZURE_ENDPOINT
can be used to set the token/model/endpoint parameters. This allows it to
be deployed in K8s and use secrets to set these environment variables
* Change document-rag and graph-rag processing so that the user can
specify parameters. Changes in Pulsar services, Pulsar message
schemas, gateway and command-line tools. User-visible changes in
new parameters on command-line tools.
* Fix bugs, graph-rag working
* Get subgraph truncation in the right place
* Graph RAG and document RAG working and configurable
* Multi-hop path traversal GraphRAG
* Add safety valve for path_size set too high
* Bring QDrant up-to-date
* Tables for data from queue outputs
- Pass single Pulsar client to everything in gateway & librarian
- Pulsar listener-name support in gateway
- PDF and text load working in librarian
* Complete Cassandra schema
* Add librarian support to templates
* - Refactored retry for rate limits into the base class
- ConsumerProducer is derived from Consumer to simplify code
- Added rate_limit_count metrics for rate limit events
* Add rate limit events to VertexAI and Google AI Studio
* Added Grafana rate limit dashboard
* Add rate limit handling to all LLMs
- Removed unused LLM client configuration from agent-manager-react
- Change agent-manager-react template to use prompt-rag instead of
prompt
- Changed TextCompletion tool to use 'question' instead of 'computation'
for its parameter.
* Make schema changes
* Core entity context flow in place
* extract-def outputs entity contexts
* Refactored qdrant write
* Refactoring of all vector stores in place
* Fix invalid variable name invocation
* Fix error responses in websockets
* Increase websocket limits to 50MB max message. Turn on Pulsar chunking by default.
similar to ServiceRequestor, but one-way.
- This means these two services are now available over websocket with
document-load and text-load service IDs.
