Kaveen Kumarasinghe

Results 16 issues of Kaveen Kumarasinghe

Hi there, first of all, I'd like to say that your project is amazing and is enabling great new functionalities for my open source projects. I'm about to release a...

No matter what I do it seems like that the knowledge graph structure always hits rate limits upon indexing: ``` llm_predictor_deep = LLMPredictor( llm=OpenAI(model_name="text-davinci-003", temperature=0, max_tokens=-1) ) index = await...

![image](https://user-images.githubusercontent.com/21161101/222315905-4b27a097-97ee-4f80-a07b-1e16db442eea.png) The query refining pipeline when doing a query seems to be a little broken (I guess the Q&A / pipeline prompt will need adjustment for chatgpt?), it seems to...

``` Traceback (most recent call last): File "/home/gptbot/cogs/search_service_cog.py", line 322, in on_message response, stdout_output = await capture_stdout( File "/home/gptbot/cogs/search_service_cog.py", line 79, in capture_stdout result = await func(*args, **kwargs) File "/usr/lib/python3.9/concurrent/futures/thread.py",...

``` return session.request(method=method, url=url, **kwargs) File "/usr/local/lib/python3.9/dist-packages/requests/sessions.py", line 587, in request resp = self.send(prep, **send_kwargs) File "/usr/local/lib/python3.9/dist-packages/requests/sessions.py", line 695, in send adapter = self.get_adapter(url=request.url) File "/usr/local/lib/python3.9/dist-packages/requests/sessions.py", line 792, in get_adapter...

Make things like code chat, internet chat, index chat persistent across restarts like the pickled /gpt converse conversations

enhancement
help wanted
good first issue
high-prio

https://replicate.com/meta/musicgen

enhancement

Just like /gpt converse, allow other conversations to also be shared when ending a conversation using sharegpt service

Add images used in chat to the sharegpt, fix the user icon not working properly

Currently if you converse with gpt vision, it will always interpret if you want to draw something or not using a separate API call, this is a second API call...

help wanted
good first issue
high-prio