mlow/lmcli
1
0
Fork 0
Code Issues 3 Pull Requests Packages Projects Releases Wiki Activity
203 Commits 3 Branches 0 Tags 1.6 MiB
60a474d516
Commit Graph

181 Commits

Author SHA1 Message Date
Matt Low
cef87a55d8 tui: initial wiring of different "app states" 2024-03-30 20:50:33 -06:00
Matt Low
29519fa2f3 Add -a/-c shorthands for lmcli list --all/--count 2024-03-30 20:50:20 -06:00
Matt Low
2e3779ad32 tui: remove temporary edit file 2024-03-29 22:26:28 +00:00
Matt Low
9cd28d28d7 tui: renamed uiCache to views, cleanup 2024-03-29 20:56:39 +00:00
Matt Low
0b991800d6 tui: dynamic input textarea height and styling updates 
Maintain a height of 4 up to half of the main content area

Add rounded border
 2024-03-29 20:00:28 +00:00
Matt Low
5af857edae tui: truncate title to width 2024-03-29 15:48:50 +00:00
Matt Low
3e24a54d0a tui: add border above input 2024-03-28 06:53:39 +00:00
Matt Low
a669313a0b tui: add tool rendering 
cleaned up message rendering and changed cache semantics

other smaller tweaks
 2024-03-26 08:06:46 +00:00
Matt Low
6310021dca tui: improve footer truncation 2024-03-23 04:08:48 +00:00
Matt Low
ef929da68c tui: add uiCache 
Clean up/fix how we calculate the height of the content viewport
 2024-03-23 03:55:20 +00:00
Matt Low
c51644e78e Add dir_tree tool 2024-03-22 20:30:34 +00:00
Matt Low
91c74d9e1e Update CreateChatCompletion behavior 
When the last message in the passed messages slice is an assistant
message, treat it as a partial message that is being continued, and
include its content in the newly created reply

Update TUI code to handle new behavior
 2024-03-22 20:02:28 +00:00
Matt Low
3185b2d7d6 tui: show the message position when focused 2024-03-17 22:55:02 +00:00
Matt Low
6c64f21d9a tui: support for message retry/continue 
Better handling of persistence, and we now ensure the response we
persist is trimmed of whitespace, particularly important when a response
is cancelled mid-stream
 2024-03-17 22:55:02 +00:00
Matt Low
6f737ad19c tui: handle text wrapping ourselves, add ctrl+w wrap toggle 
Gets rid of those pesky trailing characters
 2024-03-17 22:55:02 +00:00
Matt Low
a8ffdc156a tui: open input/messages for editing in $EDITOR 2024-03-17 22:55:02 +00:00
Matt Low
7a974d9764 tui: add ability to select a message 2024-03-17 22:55:02 +00:00
Matt Low
adb61ffa59 tui: conversation rendering tweaks, remove input character limit 2024-03-17 22:55:02 +00:00
Matt Low
1c7ad75fd5 tui: fixed response cancelling 2024-03-17 22:55:02 +00:00
Matt Low
613aa1a552 tui: ctrl+r to retry previous message 2024-03-17 22:55:02 +00:00
Matt Low
71833b89cd tui: fixed footer styling 2024-03-17 22:55:02 +00:00
Matt Low
2ad93394b1 tui: removed scrollbar 2024-03-17 22:55:02 +00:00
Matt Low
f49b772960 tui: minor fixed and cleanup 2024-03-17 22:55:02 +00:00
Matt Low
29d8138dc0 tui: update lodos 2024-03-17 22:55:02 +00:00
Matt Low
3756f6d9e4 tui: add response waiting spinner 2024-03-17 22:55:02 +00:00
Matt Low
41916eb7b3 tui: add LLM response error handling 
+ various other small tweaks
 2024-03-17 22:55:02 +00:00
Matt Low
3892e68251 tui: add a "scroll bar" and error view 2024-03-17 22:55:02 +00:00
Matt Low
8697284064 tui: generate titles for conversations 2024-03-17 22:55:02 +00:00
Matt Low
383d34f311 tui: persist new conversations as well 2024-03-17 22:55:02 +00:00
Matt Low
ac0e380244 tui: add reply persistence 2024-03-17 22:55:02 +00:00
Matt Low
c3a3cb0181 tui: improve footer rendering 
Made it easier to add segmemts later, better handling of padding
 2024-03-17 22:55:02 +00:00
Matt Low
612ea90417 tui: slight function order change 2024-03-17 22:55:02 +00:00
Matt Low
94508b1dbf tui: cache highlighted messages 
Syntax highlighting is fairly expensive, and this means we no longer
need to do syntax highlighting on the entire conversaion each time a new
message chunk is received
 2024-03-17 22:55:02 +00:00
Matt Low
7e002e5214 tui: adjust message header styling 2024-03-17 22:55:02 +00:00
Matt Low
48e4dea3cf tui: style tweaks 2024-03-17 22:55:02 +00:00
Matt Low
0ab552303d tui: add contentStyle, applied to overall viewport content 2024-03-17 22:55:02 +00:00
Matt Low
6ce42a77f9 tui: update TODO 2024-03-17 22:55:02 +00:00
Matt Low
2cb1a0005d tui: fix conversation loading 2024-03-17 22:55:02 +00:00
Matt Low
ea78edf039 tui: use EnabledTools from lmcli.Context 2024-03-17 22:55:02 +00:00
Matt Low
793aaab50e tui: styling tweak 2024-03-17 22:55:02 +00:00
Matt Low
5afc9667c7 tui: add header with title 2024-03-17 22:55:02 +00:00
Matt Low
dfafc573e5 tui: handle multi part responses 2024-03-17 22:55:02 +00:00
Matt Low
97f81a0cbb tui: scroll content view with output 
clean up msgResponseChunk handling
 2024-03-17 22:55:02 +00:00
Matt Low
eca120cde6 tui: ability to cancel request in flight 2024-03-17 22:55:02 +00:00
Matt Low
12d4e495d4 tui: add focus switching between input/messages view 2024-03-17 22:55:02 +00:00
Matt Low
d8c8262890 tui: removed confirm before send, dynamic footer 
footer now rendered based on model data, instead of being set to a fixed
string
 2024-03-17 22:55:02 +00:00
Matt Low
758f74aba5 tui: use ctx chroma highlighter 2024-03-17 22:55:02 +00:00
Matt Low
1570c23d63 Add initial TUI 2024-03-17 22:55:02 +00:00
Matt Low
46149e0b67 Attempt to fix anthropic tool calling 
Models have been way too eager to use tools when the task does not
require it (for example, reading the filesystem in order to show an
code example)
 2024-03-17 22:55:02 +00:00
Matt Low
c2c61e2aaa Improve title generation prompt performance 
The previous prompt was utterly broken with Anthropic models, they would
just try to continue the conversation
 2024-03-17 22:55:02 +00:00
Matt Low
5e880d3b31 Lead anthropic function call XML with newline 2024-03-17 22:55:02 +00:00
Matt Low
62f07dd240 Fix double reply callback on tool calls 2024-03-17 22:55:02 +00:00
Matt Low
ec1f326c2a Add store.AddReply 2024-03-14 06:01:42 +00:00
Matt Low
db116660a5 Removed tool usage logging to stdout 2024-03-14 06:01:42 +00:00
Matt Low
32eab7aa35 Update anthropic function/tool calling 
Strip the function call XML from the returned/saved content, which
should allow for model switching between openai/anthropic (and
others?) within the same conversation involving tool calls.

This involves reconstructing the function call XML when sending requests
to anthropic
 2024-03-12 20:54:02 +00:00
Matt Low
91d3c9c2e1 Update ChatCompletionClient 
Instead of CreateChatCompletion* accepting a pointer to a slice of reply
messages, it accepts a callback which is called with each successive
reply the conversation.

This gives the caller more flexibility in how it handles replies (e.g.
it can react to them immediately now, instead of waiting for the entire
call to finish)
 2024-03-12 20:39:34 +00:00
Matt Low
8bdb155bf7 Update ChatCompletionClient to accept context.Context 2024-03-12 18:24:46 +00:00
Matt Low
045146bb5c Moved flag 2024-03-12 08:03:04 +00:00
Matt Low
2c7bdd8ebf Store enabled tools in lmcli.Context 2024-03-12 08:01:53 +00:00
Matt Low
7d56726c78 Add --model flag completion 2024-03-12 07:43:57 +00:00
Matt Low
f2c7d2bdd0 Store ChromaHighlighter in lmcli.Context and use it 
In preparation for TUI
 2024-03-12 07:43:40 +00:00
Matt Low
0a27b9a8d3 Project refactor, add anthropic API support 
- Split pkg/cli/cmd.go into new pkg/cmd package
- Split pkg/cli/functions.go into pkg/lmcli/tools package
- Refactor pkg/cli/openai.go to pkg/lmcli/provider/openai

Other changes:

- Made models configurable
- Slight config reorganization
 2024-03-12 01:01:19 -06:00
Matt Low
2611663168 Add --count flag to list command, lower default from 25 to 5 2024-02-22 05:07:16 +00:00
Matt Low
120e61e88b Fixed variable shadowing bug in ls command 2024-02-22 05:00:46 +00:00
Matt Low
51ce74ad3a Add --offset flag to edit command 2024-01-09 18:10:05 +00:00
Matt Low
b93ee94233 Rename lsCmd to listCmd, add ls as an alias 2024-01-03 17:45:02 +00:00
Matt Low
db788760a3 Adjust help messages 2024-01-03 17:27:58 +00:00
Matt Low
242ed886ec Show lmcli usage by default 2024-01-03 17:27:58 +00:00
Matt Low
02a23b9035 Add clone command 
Used RunE instead of Run, make adjustments to rootCmd so that we control
how error messages are printed (in main())
 2024-01-03 17:26:57 +00:00
Matt Low
b3913d0027 Add limit to number of conversations shown by default by lmcli ls 2024-01-03 17:26:09 +00:00
Matt Low
1184f9aaae Changed how conversations are grouped by age in lmcli ls 2024-01-03 17:26:09 +00:00
Matt Low
a25d0d95e8 Don't export some additional functions, rename slightly 2024-01-03 17:24:52 +00:00
Matt Low
becaa5c7c0 Redo flag descriptions 2024-01-03 05:50:16 +00:00
Matt Low
239ded18f3 Add edit command 
Various refactoring:
- reduced repetition with conversation message handling
- made some functions internal
 2024-01-02 04:31:21 +00:00
Matt Low
59e78669c8 Fix CreateChatCompletion 
Don't double-append toolReplies
 2023-12-06 05:51:14 +00:00
Matt Low
1966ec881b Make lmcli rm allow removing multiple conversations 2023-12-06 05:51:14 +00:00
Matt Low
1e8ff60c54 Add lmcli rename to rename conversations 2023-11-29 15:33:25 +00:00
Matt Low
f206334e72 Use MessageRole constants elsewhere 2023-11-29 05:57:38 +00:00
Matt Low
5615051637 Improve config handling 
- Backup existing config if we're saving it to add configuration
  defaults
- Output messages when saving/backing up the configuration file
 2023-11-29 05:54:05 +00:00
Matt Low
d32e9421fe Add openai.enabledTools config key 
By default none are, they must be explicitly enabled by the user adding
the configuration.
 2023-11-29 05:27:58 +00:00
Matt Low
e29dbaf2a3 Code deduplication 2023-11-29 05:15:32 +00:00
Matt Low
c64bc370f4 Don't include system message when generating conversation title 2023-11-29 04:51:38 +00:00
Matt Low
4f37ed046b Delete 'retried' messages in lmcli retry 2023-11-29 04:50:45 +00:00
Matt Low
ed6ee9bea9 Add *Message[] parameter to CreateChatCompletion methods 
Allows replies (tool calls, user-facing messges) to be added in sequence
as CreateChatCompleion* recurses into itself.

Cleaned up cmd.go: no longer need to create a Message based on the
string content response.
 2023-11-29 04:43:53 +00:00
Matt Low
e850c340b7 Add initial support for tool/function calling 
Adds the following tools:
- read_dir - list a directory's contents
- read_file - read the content of a file
- write_file - write contents to a file
- insert_file_lines - insert lines in a file
- replace_file_lines - replace or remove lines in a file
 2023-11-27 05:26:20 +00:00
Matt Low
1e63c09907 Update prompt used to generate conversation title 2023-11-27 05:21:41 +00:00
Matt Low
2f3d95356a Be explicit with openai response choices limit (n parameter) 2023-11-25 13:39:52 -07:00
Matt Low
137c568129 Minor cleanup 2023-11-25 01:26:37 +00:00
Matt Low
c02b21ca37 Refactor the last refactor :) 
Removed HandlePartialResponse, add LLMRequest which handles all common
logic of making LLM requests and returning/showing their response.
 2023-11-24 15:17:24 +00:00
Matt Low
6249fbc8f8 Refactor streamed response handling 
Update CreateChangeCompletionStream to return the entire response upon
stream completion. Renamed HandleDelayedResponse to
HandleDelayedContent, which no longer returns the content.

Removes the need wrapping HandleDelayedContent in an immediately invoked
function and the passing of the completed response over a channel. Also
allows us to better handle the case of partial a response.
 2023-11-24 03:45:43 +00:00
Matt Low
a2bd911ac8 Add retry and continue commands 2023-11-22 06:53:22 +00:00
Matt Low
cb9e27542e Add --system-prompt and --system-prompt-file flags 
These allow to set a different system prompt for conversations and
one-shot prompts.

Also add a new `modelDefaults.systemPrompt` configuration key to define
the default system prompt, which can be overriden per-execution with the
--system-prompt or --system-prompt-file flags.
 2023-11-22 04:45:06 +00:00
Matt Low
db27a22347 Removed 'get' prefix from DataDir() and ConfigDir() 2023-11-22 03:17:13 +00:00
Matt Low
c8a1e3e105 Allow message input from either args or editor on all relevant commands 
Those (sub-)commands being: `new`, `reply`, and `prompt`
 2023-11-20 16:50:56 +00:00
Matt Low
b5f066ff34 Increase max token length for conversation title generation 2023-11-20 03:48:32 +00:00
Matt Low
e6dcefacf5 Add syntax highlighting 2023-11-19 05:00:59 +00:00
Matt Low
8780856854 Set config defaults using a "default" struct tag 
Add new SetStructDefaults function to handle the "defaults" struct tag.

Only works on struct fields which are pointers (in order to be able to
distinguish between not set (nil) and zero values). So, the Config
struct has been updated to use pointer fields and we now need to
dereference those pointers to use them.
 2023-11-19 04:37:14 +00:00
Matt Low
6426b04e2c Add RenderConversation to split out common message rendering logic 2023-11-18 16:17:13 +00:00
Matt Low
965043c908 Add --model flag to control which language model to use 2023-11-18 16:17:13 +00:00
Matt Low
8bc8312154 Add --length flag to control model output "maxTokens" 2023-11-18 16:17:13 +00:00