The current fix should improve Khoj responses when charts in response
context. It truncates code context before sharing with response chat actors.
Previously Khoj would respond with it not being able to create chart
but than have a generated chart in it's response in default mode.
The truncate code context was added to research chat actor for
decision making but it wasn't added to conversation response
generation chat actors.
When khoj generated charts with code for its response, the images in
the context would exceed context window limits.
So the truncation logic to drop all past context, including chat
history, context gathered for current response.
This would result in chat response generator 'forgetting' all for the
current response when code generated images, charts in response context.
It needs to be used across routers and processors. It being in
run_code tool makes it hard to be used in other chat provider contexts
due to circular dependency issues created by
send_message_to_model_wrapper func
Previous changes to depend on just the PROMPTRACE_DIR env var instead
of KHOJ_DEBUG or verbosity flag was partial/incomplete.
This fix adds all the changes required to only depend on the
PROMPTRACE_DIR env var to enable/disable prompt tracing in Khoj.
Pass your domain cert files via the --sslcert, --sslkey cli args.
For example, to start khoj at https://example.com, you'd run command:
KHOJ_DOMAIN=example.com khoj --sslcert example.com.crt --sslkey
example.com.key --host example.com
This sets up ssl certs directly with khoj without requiring a
reverse proxy like nginx to serve khoj behind https endpoint for
simple setups. More complex setups should, of course, still use a
reverse proxy for efficient request processing
- Track, return cost and usage metrics in chat api response
Track input, output token usage and cost of interactions with
openai, anthropic and google chat models for each call to the khoj chat api
- Collect, display and store costs & accuracy of eval run currently in progress
This provides more insight into eval runs during execution
instead of having to wait until the eval run completes.
Collect, display and store running costs & accuracy of eval run.
This provides more insight into eval runs during execution instead of
having to wait until the eval run completes.
- Previously when settings list became long the dropdown height would
overflow screen height. Now it's max height is clamped and y-scroll
- Previously the dropdown content would take width of content. This
would mean the menu could sometimes be less wide than the button. It
felt strange. Now dropdown content is at least width of parent button
- Track input, output token usage and cost for interactions
via chat api with openai, anthropic and google chat models
- Get usage metadata from OpenAI using stream_options
- Handle openai proxies that do not support passing usage in response
- Add new usage, end response events returned by chat api.
- This can be optionally consumed by clients at a later point
- Update streaming clients to mark message as completed after new
end response event, not after end llm response event
- Ensure usage data from final response generation step is included
- Pass usage data after llm response complete. This allows gathering
token usage and cost for the final response generation step across
streaming and non-streaming modes
- Previously online chat actors, director tests only worked with openai.
This change allows running them for any supported onlnie provider
including Google, Anthropic and Openai.
- Enable online/offline chat actor, director in two ways:
1. Explicitly setting KHOJ_TEST_CHAT_PROVIDER environment variable to
google, anthropic, openai, offline
2. Implicitly by the first API key found from openai, google or anthropic.
- Default offline chat provider to use Llama 3.1 3B for faster, lower
compute test runs
- Set output mode to single string. Specify output schema in prompt
- Both thesee should encourage model to select only 1 output mode
instead of encouraging it in prompt too many times
- Output schema should also improve schema following in general
- Standardize variable, func name of io selector for readability
- Fix chat actors to test the io selector chat actor
- Make chat actor return sources, output separately for better
disambiguation, at least during tests, for now
- Evaluate khoj on random 200 questions from each of google frames and openai simpleqa benchmarks across *general*, *default* and *research* modes
- Run eval with Gemini 1.5 Flash as test giver and Gemini 1.5 Pro as test evaluator models
- Trigger eval workflow on release or manually
- Make dataset, khoj mode and sample size configurable when triggered via manual workflow
- Enable Web search, webpage read tools during evaluation
- JSON extract from LLMs is pretty decent now, so get the input tools and output modes all in one go. It'll help the model think through the full cycle of what it wants to do to handle the request holistically.
- Make slight improvements to tool selection indicators
Previously, we'd replace the generated message with an error message
when message generation stopped via stop button on chat page of web app.
So the partially generated message (which could be useful) gets lost.
This change just stops generation, while keeping the generated
response so any useful information from the partially generated
message can be retrieved.
