Commit Graph

252 Commits

Author SHA1 Message Date
Marshall Bowers
0d0ce95eae
Replace lazy_static! with OnceLock in ai crate (#8647)
This PR replaces a `lazy_static!` usage in the `ai` crate with
`OnceLock` from the standard library.

This allows us to drop the `lazy_static` dependency from this crate.

Release Notes:

- N/A
2024-02-29 23:37:20 -05:00
Marshall Bowers
eb1ab69606
Wire up Azure OpenAI completion provider (#8646)
This PR wires up support for [Azure
OpenAI](https://learn.microsoft.com/en-us/azure/ai-services/openai/overview)
as an alternative AI provider in the assistant panel.

This can be configured using the following in the settings file:

```json
{
  "assistant": {
    "provider": {
      "type": "azure_openai",
      "api_url": "https://{your-resource-name}.openai.azure.com",
      "deployment_id": "gpt-4",
      "api_version": "2023-05-15"
    }
  },
}
```

You will need to deploy a model within Azure and update the settings
accordingly.

Release Notes:

- N/A
2024-02-29 22:01:33 -05:00
Marshall Bowers
dab886f479
Stub out support for Azure OpenAI (#8624)
This PR stubs out support for [Azure
OpenAI](https://learn.microsoft.com/en-us/azure/ai-services/openai/overview)
within the `OpenAiCompletionProvider`.

It still requires some additional wiring so that it is accessible, but
the necessary hooks should be in place now.

Release Notes:

- N/A
2024-02-29 13:02:08 -05:00
Yesterday17
9e17018416
Allow OpenAI API URL to be configured via assistant.openai_api_url (#7552)
Partially fixes #4321, since Azure OpenAI API can be converted to OpenAI
API.

Release Notes:

- Added `assistant.openai_api_url` setting to allow OpenAI API URL to be
configured.

---------

Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
2024-02-12 11:37:27 -05:00
Todsaporn Banjerdkit
2aa8ccd6b1
fix: use OPEN_AI_API_URL (#7484)
Release Notes:

- N/A
2024-02-07 10:13:52 +01:00
Todsaporn Banjerdkit
1ab49fdbe6
Use fallback BPE if the language model doesn't have one (#6848)
Release Notes:

- Added a fallback BPE if the language model doesn't have one.

---------

Co-authored-by: Piotr Osiewicz <24362066+osiewicz@users.noreply.github.com>
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
2024-01-29 22:42:03 -05:00
Marshall Bowers
027f055841
Update casing of "OpenAI" in identifiers to match Rust conventions (#6940)
This PR updates the casing of "OpenAI" when used in Rust identifiers to
match the [Rust naming
guidelines](https://rust-lang.github.io/api-guidelines/naming.html):

> In `UpperCamelCase`, acronyms and contractions of compound words count
as one word: use `Uuid` rather than `UUID`, `Usize` rather than `USize`
or `Stdin` rather than `StdIn`.

Release Notes:

- N/A
2024-01-28 12:01:10 -05:00
Antonio Scandurra
25a7eb27d2 Move interaction with keychain off the main thread 2024-01-24 14:53:05 +01:00
Antonio Scandurra
22046ef9a7 Load language models in the background 2024-01-24 13:36:44 +01:00
Piotr Osiewicz
6c82380232 chore: Fix clippy::needless_borrow up to an editor 2024-01-21 15:03:24 +01:00
Mikayla
57400e9687
Fix typos detected by crate-ci/typos 2024-01-17 14:31:21 -08:00
Piotr Osiewicz
d475f1373a
gpui: Further docs refinement & moved some reexports into 'private' module (#3935)
This commit mostly fixes invalid URLs in docstrings. It also
encapsulates crates we reexport (serde stuff + linkme) into a public
module named "private" in order to reduce the API surfaced through docs.
Moreover, I fixed up a bunch of crates that were pulling serde_json in
through gpui explicitly instead of using Cargo manifest.

Release Notes:
- N/A
2024-01-07 14:14:21 +01:00
Max Brunsfeld
4ddb26204f Remove 2 suffix for ai, zed_actions, install_ci, feature_flags
Co-authored-by: Mikayla <mikayla@zed.dev>
2024-01-03 11:48:46 -08:00
KCaverly
d5b6300fd7 moved from Boxes to Arcs for shared access of completion providers across the assistant panel and inline assistant 2023-11-02 10:08:47 -04:00
KCaverly
f3c113fe02 clean up warnings and fix tests in the ai crate 2023-10-30 11:07:24 -04:00
KCaverly
a2c3971ad6 moved authentication for the semantic index into the EmbeddingProvider 2023-10-30 10:02:27 -04:00
KCaverly
1e8b23d8fb replace api_key with ProviderCredential throughout the AssistantPanel 2023-10-28 18:16:45 -04:00
KCaverly
558f54c424 added credential provider to completion provider 2023-10-28 16:35:43 -04:00
KCaverly
7af77b1cf9 moved TestCompletionProvider into ai 2023-10-27 12:26:01 +02:00
KCaverly
ec9d79b6fe add concept of LanguageModel to CompletionProvider 2023-10-27 08:51:30 +02:00
KCaverly
6c8bb4b05e ensure OpenAIEmbeddingProvider is using the provider credentials 2023-10-27 08:33:35 +02:00
KCaverly
ca82ec8e8e fixed truncation error in fake language model 2023-10-26 14:05:55 +02:00
KCaverly
3447a9478c updated authentication for embedding provider 2023-10-26 11:18:16 +02:00
KCaverly
71bc35d241 catchup with main 2023-10-25 16:31:00 +02:00
KCaverly
8ffe5a3ec7 move keychain access into semantic index as opposed to on init 2023-10-24 13:26:37 +02:00
KCaverly
0dfbfdd164 catchup with main 2023-10-23 17:21:37 +02:00
KCaverly
4e90e45999 move embedding truncation to base model 2023-10-23 14:07:45 +02:00
KCaverly
2b780ee7b2 add base model to EmbeddingProvider, not yet leveraged for truncation 2023-10-22 15:00:09 +02:00
KCaverly
d1dec8314a move OpenAIEmbeddings to OpenAIEmbeddingProvider in providers folder 2023-10-22 14:46:22 +02:00
KCaverly
d813ae8845 replace OpenAIRequest with more generalized Box<dyn CompletionRequest> 2023-10-22 14:33:19 +02:00
KCaverly
05ae978cb7 move OpenAICompletionProvider to providers location 2023-10-22 13:57:13 +02:00
KCaverly
3712794e56 move OpenAILanguageModel to providers folder 2023-10-22 13:47:28 +02:00
KCaverly
a62baf34f2 rename templates to prompts in ai crate 2023-10-22 13:46:49 +02:00
KCaverly
0b57ab7303 cleaned up truncate vs truncate start 2023-10-22 13:34:22 +02:00
KCaverly
106115676d update semantic search to use keychain as fallback 2023-10-21 10:19:50 -04:00
KCaverly
71fb23f769 decrease temperature for inline assist on code content 2023-10-19 15:44:49 -04:00
KCaverly
19c2df4822 outlined when truncation is taking place in the prompt 2023-10-19 14:33:52 -04:00
KCaverly
178a84bcf6 progress on smarter truncation strategy for file context 2023-10-18 17:56:59 -04:00
KCaverly
587fd707ba added smarter error handling for file_context prompts without provided buffers 2023-10-18 16:40:09 -04:00
KCaverly
f59f2eccd5 added dumb truncation strategies to file_context and generate 2023-10-18 16:32:14 -04:00
KCaverly
a0e01e075d fix for error when truncating a length less than the string length 2023-10-18 16:31:29 -04:00
KCaverly
32853c2044 added initial placeholder for truncation without a valid strategy 2023-10-18 16:23:53 -04:00
KCaverly
473067db31 update PromptPriority to accomodate for both Mandatory and Ordered prompts 2023-10-18 15:56:39 -04:00
KCaverly
aa1825681c update the assistant panel to use new prompt templates 2023-10-18 14:20:12 -04:00
KCaverly
b9bb27512c fix template ordering during prompt chain generation 2023-10-18 13:10:31 -04:00
KCaverly
fa61c1b9c1 add prompt template for generate inline content 2023-10-18 13:03:11 -04:00
KCaverly
178a79fc47 added prompt template for file context without truncation 2023-10-18 12:29:10 -04:00
KCaverly
02853bbd60 added prompt template for repository context 2023-10-17 17:29:07 -04:00
KCaverly
a874a09b7e added openai language model tokenizer and LanguageModel trait 2023-10-17 16:21:03 -04:00
KCaverly
ad92fe49c7 implement initial concept of prompt chain 2023-10-17 11:58:45 -04:00