Olicorne

You can use litellm to point towards OpenAI API and change the URL to point to the textgen local URL apparently.

I confirm this is working in a page block but I fail to make it work in the config.edn queries. Any idea? ``` {:title "OmnivoreToAnkify {{renderer :todomaster}}" :query [:find (pull...

I had the same issue in a gradio app. I moved the use of function `create_sync_playwright_browser` to a piece of code that was running at startup instead of in a...

In the end I moved to async and am getting the same issue : ``` [tool/start] [1:chain:AgentExecutor > 4:tool:navigate_browser] Entering Tool run with input: "{'url': 'https://duckduckgo.com/?q=sam+altman+birthdate'}" ``` **hangs indefinitely**

Are there any failsafe to avoid very high costs? I think it would be nice to be able to use "--max-budget=10" to make sure the total cost will never go...

Hi, I think keynav uses xdotool and I had a bit of trouble setting up xdotool with my own i3 binding (without keynav) because the binding used modifiers so I...

Agreed. I think that the documentation should state somewhere the exact rules that are used to know if the cache needs to be recomputed. I expected that the `__eq__` method...

Same here. Related to #1460 I use refine to summarize long articles and I see that the summary is actually quite good in the intermediate steps but at some point...

Yes same here. So the issue is from the reduce prompt and not the map prompt right? I struggle to find the reduce prompt in the codebase, can you ?

I ended up apparently fixing my problem. I basically changed a few lines to go closer to this : https://python.langchain.com/docs/use_cases/question_answering/how_to/chat_vector_db Here's my patch: ``` from langchain.chains import ConversationalRetrievalChain +from langchain.chains...