-
I can use `httpx` to stream responses from an LLM API as follows:
```.py
# ...
async with httpx.AsyncClient() as client:
start_time = time.time()
…
-
I'd like to propose adding batch processing capabilities to optimize costs when processing documents through Azure AI services. Currently, it seems each page/document requires individual API calls, wh…
-
A new approach:
- htmx-based 'front end'
- with a service worker redirecting REST requests to:
- an in-browser WASM intermediary, which:
- converts these to JSON requests, submitted to the Ch…
-
Follow up of #5348 which revealed multiple bugs in TypeScript composed types generation
## Repro
```yaml
openapi: 3.0.3
info:
title: Example
description: Example
version: 1.0.0
serve…
-
Sending works fine, however no response is ever received because the connection stays open and partial responses are not received from chatterbox.
-
See the discussion here
https://near.zulipchat.com/#narrow/stream/295302-general/topic/RPC.20tracking.20subset.20of.20shards
https://docs.google.com/document/d/1cYs6erFk2bUiqNxyPR9nWYQETHwzYEDJrRBks…
-
The points awarded for each response is:
(response: points)
- Yes: 100
- No: 0
- N/A: Redistribute points
- Does not answer question: 0
- Partial: 50
The total score is calculated by summ…
-
@faxm0dem contacted us on gitter about elasticsearch-http: partial results with bulk indexing results in a HTTP 200 status response.
Example response on a shard failure:
```
{
"took" : 3,
"…
-
We are seeing this behavior from times to times, we see a spike on invalid responses returned by the completion suggester: the options returned may be "partial".
By partial response I mean that the i…
nomoa updated
3 months ago
-
### Environment
* PostgreSQL version: 12
* PostgREST version: `postgrest/postgrest:v8.0.0`
* Operating system: AWS Linux
### Description of issue
_(Expected behavior vs actual behavior)_
…