* gptel.el (gptel--url-get-response, gptel--url-parse-response):
- When the query fails, the error message format (in the JSON)
differs between APIs. Ultimately it may be required to dispatch
error handling via a generic function, but for now: try to make
the error handling API agnostic.
- Mention the backend name in the error message. Pass the backend
to the (non-streaming response) parsers to be able to do this.
* gptel-curl.el (gptel-curl--stream-cleanup,
gptel-curl--parse-response): Same changes.
* gptel.el (gptel-request): When `gptel-request` is supplied a
string, it creates the full prompt plist according to the OpenAI
API. Fix by inserting it into a temp buffer and using the
cl-generic dispatch to parse the buffer instead. This is a janky
solution but the best possible one without defining another
generic function just to handle prompt strings differently per API.
* gptel.el (gptel--at-word-end, gptel-send, gptel-request):
Include the word the cursor is on in the prompt, and don't break
it when inserting the response. This is primarily useful for
evil-mode users who frequenty end up one char before the end of a
word when they switch to normal-mode.
* gptel-transient.el (gptel-send): Same. Also fix bug with
selecting an existing buffer to send the response to.
gptel.el (gptel--get-api-key, gptel, gptel-mode,
gptel-make-openai, gptel-api-key-from-auth-source): Handle models
that don't require an API key.
gptel-transient.el (gptel--suffix-system-message): Set backend
from buffer-local value when invoking, and handle API key
requirement better.
README.org: Update README with new information and a multi-llm demo.
gptel.el (gptel-host, gptel--known-backends, gptel--api-key,
gptel--create-prompt, gptel--request-data, gptel--parse-buffer, gptel-request,
gptel--parse-response, gptel--openai, gptel--debug, gptel--restore-state,
gptel, gptel-backend):
Integrate multiple LLMs through the introcution of gptel-backends. Each backend
is composed of two pieces:
1. An instance of a cl-struct, containing connection, authentication and model
information. See the cl-struct `gptel-backend` for details. A separate
cl-struct type is defined for each supported backend (OpenAI, Azure, GPT4All and
Ollama) that inherits from the generic gptel-backend type.
2. cl-generic implementations of specific tasks, like gathering up and
formatting context (previous user queries and LLM responses), parsing responses
or responses streams etc. The four tasks currently specialized this way are
carried out by `gptel--parse-buffer` and `gptel--request-data` (for constructing
the query) and `gptel--parse-response` and `gptel-curl--parse-stream` (for
parsing the response). See their implementations for details. Some effort has
been made to limit the number of times dispatching is done when reading
streaming responses.
When a backend is created, it is registered in the collection
`gptel--known-backends` and can be accessed by name later, such as from the
transient menu.
Only one of these backends is active at any time in a buffer, stored in the
buffer-local variable `gptel-backend`. Most messaging, authentication etc
accounts for the active backend, although there might be some leftovers.
When using `gptel-request` or `gptel-send`, the active backend can be changed or
let-bound.
- Obsolete `gptel-host`
- Fix the rear-sticky property when restoring sessions from files.
- Document some variables (not user options), like `gptel--debug`
gptel-openai.el (gptel-backend, gptel-make-openai, gptel-make-azure,
gptel-make-gpt4all): This file (currently always loaded) sets up the generic
backend struct and includes constructors for creating OpenAI, GPT4All and Azure
backends. They all use the same API so a single set of defgeneric
implemenations suffices for all of them.
gptel-ollama.el (gptel-make-ollama): This file includes the cl-struct,
constructor and requisite defgeneric implementations for Ollama support.
gptel-transient.el (gptel-menu, gptel-provider-variable, gptel--infix-provider,
gptel-suffix-send):
- Provide access to all available LLM backends and models from `gptel-menu`.
- Adjust keybindings in gptel-menu: setting the model and query parameters is
now bound to two char keybinds, while redirecting input and output is bound to
single keys.
gptel.el (gptel--insert-response):
gptel-curl.el (gptel-curl--stream-insert-response): Make the `gptel'
text-property rear-nonsticky so typing after it is recognized as part of the
user prompt.
* gptel.el (gptel-default-mode): Use `fboundp' instead of `featurep' to check if
markdown-mode is available, since the latter requires `markdown-mode' to be
already loaded.
* gptel.el (gptel--system-message, gptel-directives): Try to make
gptel--system-message read from gptel-directives. This doesn't yet work how
we need it to -- changing gptel-directives does not update
gptel--system-message.
* gptel.el (gptel--restore-state): When there is no "GPTEL_BOUNDS"
org property, `read' asks for stdin instead. Fix by only calling
`read' when this property is non-nil.
Thanks to @Elilif for spotting this bug.
* gptel.el (gptel--save-state, gptel--restore-state,
gptel-temperature, gptel-model, gptel-max-tokens,
gptel-directives, gptel--always, gptel--button-buttonize,
gptel--system-message, gptel--bounds): Write gptel parameters as
file-local variables when saving chats in Markdown or text files.
The local variable gptel--bounds stores the locations of the
responses from the LLM. This is not a great solution, but the best
I can think to do without adding more syntax to the document.
Chats can be restored by turning on `gptel-mode'. One of the
problem with this approach is that if the buffer is modified
before `gptel-mode' is turned on, the state data is out of date.
Another problem is that this metadata block as printed in the
buffer can become quite long. A better approach is needed.
Define helper functions `gptel--always' and
`gptel--button-buttonize' to work around Emacs 27.1 support.
* README.org: Mention saving and restoring chats where
appropriate.
* gptel.el (gptel--insert-response, gptel-pre-response-hook): New
user option `gptel-pre-response-hook' that runs before the
response is inserted into the buffer. This can be used to prepare
the buffer in some user-specified way for the response.
* gptel-curl.el (gptel-curl--stream-filter): Run
`gptel-pre-response-hook' before inserting streaming responses.
* gptel.el (gptel-mode, gptel-set-topic, gptel--create-prompt,
gptel-set-topic, gptel--get-topic-start, gptel--get-bounds,
gptel--save-state, gptel--restore-state): Add support for saving
and restoring gptel state for Org buffers. Support for Markdown
buffers is not yet implemented.
`gptel--save-state' and `gptel--restore-state' save and restores
state using Org properties. With `gptel-mode' active, these are
run automatically when saving the buffer or enabling `gptel-mode'
respectively.
The command `gptel-set-topic' can be used to set a topic for the
current heading, which is stored as an Org property. The topic
name is unused (as of now), but the presence of this property
limits the text context sent to ChatGPT to the heading text up to
the cursor position.
Autload `gptel-mode' since the user may want to enable this (to
restore sessions) without having loaded gptel.el.
gptel.el (gptel-request): when using `gptel-request', let-bind
`gptel--system-message' around call to `gptel--create-prompt' when
the prompt argument is null. This allows `gptel-request' to be
used to send the buffer as a prompt with a different system
message from `gptel--system-message' for that buffer.
---------
Co-authored-by: Neil Fulwiler <neil@fulwiler.me>
* gptel.el (gptel-crowdsourced-prompts-file): This file holds
prompts compiled by the community.
* gptel-transient.el (gptel--read-crowdsourced-prompt,
gptel--crowdsourced-prompts, gptel-system-prompt--setup,
gptel--crowdsourced-prompts-url): Fetch crowdsourced system
prompts from https://github.com/f/awesome-chatgpt-prompts and pick
one to use from the transient menu.
* gptel.el (gptel-proxy): Support a proxy when interacting with openai
endpoint. In many organizations the openai api can only be accessed
via proxy. This is easily supported by curl.
gptel-curl.el (gptel-curl--get-args): tidy up `gptel-curl--get-args'.
---------
Co-authored-by: PalaceChan <XXX>
* gptel.el (gptel-directives): Bump required transient version to
0.4.0. Remove placeholder about hard-coded directives from
the docstring for `gptel-directives'.
* gptel-transient.el (gptel-system-prompt,
gptel-system-prompt--setup): Dynamically generate the system
prompt menu in `gptel-menu'. Delete helper functions that
hard-coded the list of system prompts/directives before.
* gptel.el (gptel--insert-response):
* gptel-transient.el (gptel--suffix-send):
* gptel-curl.el (gptel-curl--stream-filter, gptel-curl--stream-insert-response,
gptel-curl--stream-cleanup):
Handle read-only gptel buffers by redirecting the output to a new buffer (that
pops up automatically). To track this,
- the `:position' argument of the INFO plist, which is a marker, is moved to the
new output buffer.
- the `:buffer' argument of the INFO plist is unmodified, it always points to
the buffer that the request originated from.
* gptel.el (gptel): `gptel' only pops to the gptel buffer when
called interactively.
* gptel-transient.el: Pop up the gptel session buffer when the
prompt is sent to it, but don't select it. Also message the user
that the response has been redirected to the gptel session.
* gptel.el (gptel-send): Replace references to `gptel-send-menu'.
* gptel-transient.el: Rename `gptel-send-menu' t `gptel-menu'.
This shorter name is apropos of its increased feature set (in the
forthcoming commits).
* gptel.el (gptel--insert-response, gptel-request):
- Add an in-place key to gptel-request. When true, the default
callbacks will not delimit the API responses with newlines.
- Add a strea option to gptel-request. Only works with the default
filter/stream-insert callback, so it's marked as for internal use
for now.
* gptel-curl.el (gptel-curl--stream-insert-response): Ditto.
* gptel.el (gptel--url-parse-response, gptel--url-get-response,
gptel--insert-response, gptel-send):
- Use shorter keys for passing the info plist,
- record errors in the info plist,
- separate user messaging from the callback and more.
- Make the API more functional (i.e. less imperative)
This is in preparation for adding `gptel-request', an API for
defining custom commands.
Note: The streaming filter and callback are mostly unchanged.
Streaming is not planned to be accessible via `gptel-request'.
* gptel-curl.el (gptel-curl--parse-response, gptel-curl--sentinel,
gptel-curl--stream-filter, gptel-curl--stream-insert-response,
gptel-curl--stream-cleanup, gptel-curl-get-response): Ditto.
* gptel.el (gptel--url-parse-response, gptel--insert-response):
Use the same error codes/descriptions across url-retrieve/Curl,
with and without streaming responses.
* gptel-curl.el (gptel-curl--parse-response,
gptel-curl--stream-filter, gptel-curl--stream-cleanup): Ditto.
* gptel.el (gptel--playback, gptel--insert-response):
`gptel--insert-response' no longer handles stream playback. Run
`gptel-post-response-hook' after inserting the response from
ChatGPT. Delete the `gptel--playback' function since it never did
anything -- it was a placebo.
* gptel.el (gptel--url-get-response, gptel--insert-response,
gptel-send): Rename the :insert-marker keyword in the async info
plist to :start-marker.
* gptel-curl.el (gptel--insert-response-stream,
gptel-curl--cleanup-stream, gptel-curl-get-response): Ditto.
* gptel.el (gptel--convert-playback-markdown->org,
gptel-post-response-hook): Add a hook that runs after the response
is received. This will allow for custom actions like moving the
cursor to the next prompt. The markdown->org stream converter now
cleans up after itself using this hook.
* gptel.el (gptel--convert-playback-markdown->org): New converter
for markdown->org that works on text chunks while maintaining the
parse state until the text stream is finished.
* gptel-curl.el (gptel--insert-response-stream,
gptel-curl-get-response): When using `gptel-playback' and
requesting ChatGPT's responses in org-mode, run the above
converter on the received response. This works by storing the
converter and associated state as a closure in the async info
plist that is supplied along with the response, and running it
repeatedly on each chunk of text in the response stream before it
is inserted into the buffer.
FIXME: Note that `gptel-response-filter-functions' is currently
ignored if using `gptel-stream'.
* gptel.el (gptel--request-data): Request a streaming message if
`gptel-stream' is non-nil.
* gptel-curl.el (gptel-curl-get-response,
gptel-curl--cleanup-stream, gptel-curl--filter): Add a process
filter and sentinel for Curl to stream ChatGPT's response into
Emacs in real-time.
* gptel.el (gptel--url-get-response,
gptel-api-key-from-auth-source): `gptel--url-get-response' accepts
a callback argument that can be used to do something besides
inserting the response into the current buffer.
* gptel-curl.el (gptel-curl--sentinel, gptel-curl-get-response):
`gptel-curl--sentinel' now accepts a callback argument that can be
used to do something besides inserting the response into the
current buffer.
These changes are in preparation for more specific functionality,
like showing the response as a message, or replacing the prompt
with the response etc.
This changes response parsing so that the response body is decoded as
UTF-8 and then parsed as JSON, rather than the other way around.
This fixes the handling of responses that contain Unicode characters
which are encoded with multiple bytes in UTF-8, such as emojis.
