karthink

> and with > ``` > (map-keys gptel--known-backends) > ``` > i obtain `("ChatGPT")` The Ollama backend is not being defined then. Does your `setq` form throw any errors? Can...

Could you paste the exact config you are using for Ollama?

```elisp (use-package gptel :config (setq-default gptel-backend (gptel-make-ollama "Ollama" :host "my-ip:11434" :models '("mistral:latest") :stream t) gptel-model "mistral:latest")) ``` ^ Let me know if this doesn't work as expected.

Have you looked at the README? Most of these questions are addressed there. > it works but i get an error: error in process filter: Search failed: "^{" Is this...

> how would i add the protocol to this Please look at the documentation of `gptel-make-ollama`. You would add the arguments `:protocol "https"` in the call to `gptel-make-ollama`. > Where...

> error in process filter: Search failed: "^{" 1. Run `(setq gptel--debug t)` 2. Try to use Ollama 3. A buffer will pop up containing the response. Please paste the...

@yhzhoucs Thanks for that! Should be fixed for everyone now.

You can use `gptel-prompt-prefix-alist` and `gptel-response-prefix-alist` to add text before a response/prompt. This is intended for use in gptel chat buffers. See #103 for an example. A more general solution...

Closing this now, please reopen if the above solution doesn't work.

None of these are features planned for gptel, so I'm moving this to discussions. To watermark text you can use `gptel-post-response-hook`, or `gptel--get-buffer-bounds`, which see.