AI/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2024-10-01 01:06:10 -04:00
Code Issues Packages Projects Releases Wiki Activity
2,049 Commits 491 Branches 56 Tags 46 MiB
244b82622c
Commit Graph

128 Commits

Author SHA1 Message Date
Adam Treat
244b82622c Implement error handling for tool calls. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-08-14 07:43:48 -04:00
Adam Treat
5fc2ff8e69 Use parameters which is in keeping with other standard practices. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-08-14 07:43:48 -04:00
Adam Treat
27b86dae21 Serialize the source excerpts from and to pure json 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-08-14 07:43:48 -04:00
Adam Treat
01f67c74ea Begin converting the localdocs to a tool. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-08-14 07:43:48 -04:00
Adam Treat
dfe3e951d4 Refactor the brave search and introduce an abstraction for tool calls. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-08-14 07:43:48 -04:00
Adam Treat
fffd9f341a Refactor to handle errors in tool calling better and add source comments. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-08-14 07:43:48 -04:00
Adam Treat
7c7558eed3 Stop hardcoding the tool call checking and rely upon the format advocated by ollama for tool calling. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-08-14 07:43:48 -04:00
Adam Treat
d2ee235388 Change the suggestion mode to turn on for tool calls by default. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-08-14 07:43:48 -04:00
Adam Treat
dda59a97a6 Fix the way we're injecting the context back into the model for web search. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-08-14 07:43:48 -04:00
Adam Treat
f4fb3df437 Brave search tool calling. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-08-14 07:43:48 -04:00
Jared Van Bortel
be66ec8ab5
chat: faster KV shift, continue generating, fix stop sequences (#2781) 
* Don't stop generating at end of context
* Use llama_kv_cache ops to shift context
* Fix and improve reverse prompt detection
* Replace prompt recalc callback with a flag to disallow context shift
 2024-08-07 11:25:24 -04:00
Jared Van Bortel
51bd01ae05
backend: fix extra spaces in tokenization and a CUDA crash (#2778) 
Also potentially improves accuracy of BOS insertion, token cache, and logit indexing.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-08-01 10:46:36 -04:00
不知火 Shiranui
f9cd2e321c
feat: add openai-compatible api models (#2683) 
Signed-off-by: Shiranui <supersonic@livemail.tw>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
 2024-07-25 10:02:52 -04:00
AT
765e055597
Change the timeout for circle ci and add a fixme. (#2722) 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-07-23 17:01:46 -04:00
Jared Van Bortel
56d5a23001
chatllm: fix loading of chats after #2676 (#2693) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-07-18 21:03:18 -04:00
AT
ca72428783
Remove support for GPT-J models. (#2676) 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
 2024-07-17 16:07:37 -04:00
AT
66bc04aa8e
chat: generate follow-up questions after response (#2634) 
* user can configure the prompt and when they appear
* also make the name generation prompt configurable

Signed-off-by: Adam Treat <treat.adam@gmail.com>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
 2024-07-10 15:45:20 -04:00
Jared Van Bortel
2c8d634b5b
UI and embedding device changes for GPT4All v3.0.0-rc3 (#2477) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-06-28 12:57:57 -04:00
Jared Van Bortel
01870b4a46
chat: fix blank device in UI and improve Mixpanel reporting (#2409) 
Also remove LLModel::hasGPUDevice.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-06-26 15:26:27 -04:00
AT
9273b49b62
chat: major UI redesign for v3.0.0 (#2396) 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
 2024-06-24 18:49:23 -04:00
Jared Van Bortel
41c9013fa4
chat: don't use incomplete types with signals/slots/Q_INVOKABLE (#2408) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-06-06 11:59:28 -04:00
Jared Van Bortel
d3d777bc51
chat: fix #includes with include-what-you-use (#2401) 
Also use qGuiApp instead of qApp.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-06-04 14:47:11 -04:00
Jared Van Bortel
d2a99d9bc6
support the llama.cpp CUDA backend (#2310) 
* rebase onto llama.cpp commit ggerganov/llama.cpp@d46dbc76f
* support for CUDA backend (enabled by default)
* partial support for Occam's Vulkan backend (disabled by default)
* partial support for HIP/ROCm backend (disabled by default)
* sync llama.cpp.cmake with upstream llama.cpp CMakeLists.txt
* changes to GPT4All backend, bindings, and chat UI to handle choice of llama.cpp backend (Kompute or CUDA)
* ship CUDA runtime with installed version
* make device selection in the UI on macOS actually do something
* model whitelist: remove dbrx, mamba, persimmon, plamo; add internlm and starcoder2

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-05-15 15:27:50 -04:00
Jared Van Bortel
7e1e00f331
chat: fix issues with quickly switching between multiple chats (#2343) 
* prevent load progress from getting out of sync with the current chat
* fix memory leak on exit if the LLModelStore contains a model
* do not report cancellation as a failure in console/Mixpanel
* show "waiting for model" separately from "switching context" in UI
* do not show lower "reload" button on error
* skip context switch if unload is pending
* skip unnecessary calls to LLModel::saveState

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-05-15 14:07:03 -04:00
Jared Van Bortel
7f1c3d4275
chatllm: fix model loading progress showing "Reload" sometimes (#2337) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-05-15 13:57:53 -04:00
Jared Van Bortel
5fb9d17c00
chatllm: use a better prompt for the generated chat name (#2322) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-05-09 09:38:19 -04:00
Jared Van Bortel
adaecb7a72
mixpanel: improved GPU device statistics (plus GPU sort order fix) (#2297) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-05-01 16:15:48 -04:00
Jared Van Bortel
c622921894
improve mixpanel usage statistics (#2238) 
Other changes:
- Always display first start dialog if privacy options are unset (e.g. if the user closed GPT4All without selecting them)
- LocalDocs scanQueue is now always deferred
- Fix a potential crash in magic_match
- LocalDocs indexing is now started after the first start dialog is dismissed so usage stats are included

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-25 13:16:52 -04:00
Jared Van Bortel
271d752701
localdocs: small but important fixes to local docs (#2236) 
* chat: use .rmodel extension for Nomic Embed

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

* database: fix order of SQL arguments in updateDocument

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

---------

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-18 14:51:13 -04:00
Jared Van Bortel
ac498f79ac
fix regressions in system prompt handling (#2219) 
* python: fix system prompt being ignored
* fix unintended whitespace after system prompt

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-15 11:39:48 -04:00
Olyxz16
2c0a660e6e
feat: Add support for Mistral API models (#2053) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Signed-off-by: Cédric Sazos <cedric.sazos@tutanota.com>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-13 18:23:57 -04:00
Jared Van Bortel
406e88b59a
implement local Nomic Embed via llama.cpp (#2086) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-13 18:09:24 -04:00
Xu Zhen
0072860d24 Fix compatibility with Qt 6.4 
Signed-off-by: Xu Zhen <xuzhen@users.noreply.github.com>
 2024-03-12 07:42:22 -05:00
Adam Treat
17dee02287 Fix for issue #2080 where the GUI appears to hang when a chat with a large 
model is deleted. There is no reason to save the context for a chat that
is being deleted.

Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-06 16:52:17 -06:00
Jared Van Bortel
44717682a7
chat: implement display of model loading warnings (#2034) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-06 17:14:54 -05:00
Jared Van Bortel
a0bd96f75d
chat: join ChatLLM threads without calling destructors (#2043) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-06 16:42:59 -05:00
Jared Van Bortel
2a91ffd73f chatllm: fix undefined behavior in resetContext 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-06 12:54:19 -06:00
chrisbarrera
f8b1069a1c
add min_p sampling parameter (#2014) 
Signed-off-by: Christopher Barrera <cb@arda.tx.rr.com>
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
 2024-02-24 17:51:34 -05:00
Adam Treat
67bbce43ab Fix state issues with reloading model. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-02-21 16:05:49 -05:00
Jared Van Bortel
4fc4d94be4
fix chat-style prompt templates (#1970) 
Also use a new version of Mistral OpenOrca.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-02-21 15:45:32 -05:00
Adam Treat
fa0a2129dc Don't try and detect model load error on startup. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-02-21 10:15:20 -06:00
Adam Treat
67099f80ba Add comment to make this clear. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-02-21 10:15:20 -06:00
Adam Treat
d948a4f2ee Complete revamp of model loading to allow for more discreet control by 
the user of the models loading behavior.

Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-02-21 10:15:20 -06:00
Adam Treat
4461af35c7 Fix includes. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-02-05 16:46:16 -05:00
Jared Van Bortel
10e3f7bbf5
Fix VRAM leak when model loading fails (#1901) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-02-01 15:45:45 -05:00
Adam Treat
d14b95f4bd Add Nomic Embed model for atlas with localdocs. 2024-01-31 22:22:08 -05:00
Jared Van Bortel
061d1969f8
expose n_gpu_layers parameter of llama.cpp (#1890) 
Also dynamically limit the GPU layers and context length fields to the maximum supported by the model.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-01-31 14:17:44 -05:00
Jared Van Bortel
c7ea283f1f
chatllm: fix deserialization version mismatch (#1859) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-01-22 10:01:31 -05:00
Jared Van Bortel
d1c56b8b28
Implement configurable context length (#1749) 2023-12-16 17:58:15 -05:00
Jared Van Bortel
0600f551b3
chatllm: do not attempt to serialize incompatible state (#1742) 2023-12-12 11:45:03 -05:00