eeb00a5ca2
chore: format
2025-02-20 01:01:29 -08:00
2b913a99a3
Merge pull request #10417 from hangxingliu/liu/fix-build-proxy
...
build: load the proxy from the system env for Pyodide to download packages
2025-02-20 00:58:27 -08:00
0994a07874
Merge pull request #10415 from labanzu/better-pdf-preview
...
feat: better pdf preview
2025-02-20 00:57:11 -08:00
a818d8e3b7
Merge pull request #10413 from dom133/dev
...
i18n: Improve Polish translation
2025-02-20 00:55:52 -08:00
3ae7302f7b
build: load the proxy from the system env for Pyodide to download packages #6234
2025-02-20 16:40:31 +08:00
9ba03523e7
i18n: Improve Polish translation
2025-02-20 09:26:07 +01:00
f4e67bf2d3
update
2025-02-20 16:10:29 +08:00
a3d3ca293e
chore: optimize pdf view
2025-02-20 15:55:18 +08:00
d6f3444141
fix: katex issue
2025-02-19 23:37:11 -08:00
0e20b15afe
Merge pull request #10410 from xinhai-ai/dev
...
fix: GitHub OAuth email retrieval when public email is not set
2025-02-19 23:16:46 -08:00
e1cc104805
Merge pull request #10408 from hangxingliu/liu/fix-proxy
...
fix: respect proxy and timeout settings in audio-related aiohttp requests
2025-02-19 23:16:15 -08:00
de8492de34
fix: GitHub OAuth email retrieval when public email is not set
2025-02-20 15:06:07 +08:00
90d9cdacfa
fix: respect proxy and timeout settings in audio-related aiohttp requests
2025-02-20 14:55:45 +08:00
13e58c1b64
Merge pull request #10360 from ferret99gt/ollama-option-conversion-fixes
...
fix: Update Ollama option handling in payload.py's convert_payload_openai_to_ollama
2025-02-19 22:44:07 -08:00
d5a049dc54
Merge pull request #10401 from xinhai-ai/main
...
fix: email claim doesn't effect
2025-02-19 20:43:43 -08:00
dec44e4bcd
Fix: email claim doesn't effect
2025-02-20 11:32:48 +08:00
ae0554224a
refac
2025-02-19 18:22:31 -08:00
fe5c4b95d5
enh: configurable jupyter execution timeout
2025-02-19 17:05:37 -08:00
90fca993f3
wip: jupyter code excution timeout
2025-02-19 16:41:54 -08:00
efefff71d1
Merge pull request #10363 from ferret99gt/ollama-model-option-conversion-updates
...
feat: Update Payload's apply_model_params_to_body_ollama with full Ollama supported options
2025-02-19 12:32:46 -08:00
5da47de6eb
Merge pull request #10366 from tarmst/fix-no-nested-claims-for-group-oauth
...
Fix: Add nested claim search for group oauth management
2025-02-19 12:23:54 -08:00
b032f34831
Merge pull request #10364 from Lutherwaves/translations
...
i18n: Add bulgarian translations
2025-02-19 12:23:30 -08:00
ea4ad3944c
Merge pull request #10378 from Seniorsimo/message-conversion
...
**fix** Add support for tool message in openai to Ollama message conversion
2025-02-19 12:23:11 -08:00
ea3f873ae9
Merge pull request #10377 from Seniorsimo/chat-message-validator
...
**fix** ChatMessage validator: content can be null when using tools
2025-02-19 12:22:31 -08:00
de7e8fd918
Merge pull request #10362 from Seniorsimo/usage-openai-compatible
...
**fix** Added OpenAI usage standard keys to API signature
2025-02-19 12:20:41 -08:00
17560967c7
Merge pull request #10347 from Youggls/dev
...
fix(deps): upgrade pydantic from v2.9.2 to v2.10.3+ in requirements.txt and pyproject.toml
2025-02-19 12:18:51 -08:00
9a4f2b9aa3
Merge pull request #10354 from TiancongLx/dev
...
i18n: update zh-TW
2025-02-19 12:18:32 -08:00
6f698073bb
Add support for tool message in openai to Ollama message conversion
2025-02-19 21:11:39 +01:00
8662108344
Fix on ChatMessage validator: content can be null when using tools
2025-02-19 21:03:23 +01:00
efe3bca19e
Add nested claim search for groups oauth claim
2025-02-19 16:47:52 +00:00
6898fd7d0f
chore: Add bulgarian translations
2025-02-19 17:35:56 +02:00
5701d6d333
Change the opt dictionary to a mappings dictionary with appropriate casts
...
This is to bring consistency with apply_model_params_to_body_openai. Both now use a mapping dictionary then call and return apply_model_params_to_body directly.
2025-02-19 09:30:16 -05:00
074ce356de
Added OpenAI usagerequested keys
2025-02-19 15:28:39 +01:00
fa885c3346
Update remapping logic
...
We copy the params from from the original key to the new key, then delete it. This is to ensure Ollama only gets valid options.
(Add a comment as well)
2025-02-19 09:25:47 -05:00
a4249a6351
Remove remapping of frequency_penalty to repeat_penalty
...
1) Ollama natively supports frequency_penalty, so this is not necessary.
2) Repeat_penalty is being added to Open WebUI in PR #10016 , allowing Ollama users to pick which penalty methods they want.
2025-02-19 09:24:38 -05:00
877d21a029
Move parameter remapping above the opt dictionary.
...
This is so that any remappings are handled before options are handled by apply_model_params_to_body
2025-02-19 09:23:33 -05:00
6b2ba73701
Remove tfs_z
...
See https://github.com/ollama/ollama/blob/main/docs/api.md#request-8
tfs_z was removed from Llama.cpp and Ollama in January 2025.
2025-02-19 09:21:36 -05:00
cee08e316d
Update Ollama request option list with full supported options
...
See https://github.com/ollama/ollama/blob/main/docs/api.md#request-8
This adds the full suite of supported Ollama options.
2025-02-19 09:21:05 -05:00
8125b0499b
Remove empty ollama_options
...
1) The empty dictionary from line 176 is never used.
2) Lines 193-194 are not necessary as they were already done at line 177
2025-02-19 08:57:05 -05:00
57b01cf8fb
Fix for system prompt setting
...
1) Ollama supports sending the system prompt as a parameter, not as an option. (See https://github.com/ollama/ollama/blob/main/docs/api.md#request-8 ) However, it is in the options dictionary and needs moved to the payload dictionary.
2) After moving the system parameter from ollama_options to ollama_payload, delete it from ollama_options. This is to prevent Ollama throwing a warning about invalid options.
2025-02-19 08:55:11 -05:00
fea169a9c0
Core fix for num_predict not working.
...
1) max_tokens was being looked for in openai_payload, but is present in openai_payload['options'], so is never found.
2) After copying the value for max_tokens to num_predict, delete max_tokens from the dictionary. This is to prevent Ollama throwing a warning about invalid option (max_tokens)
2025-02-19 08:52:34 -05:00
adde37394b
Remove parameters that map directly, as they are part of options
...
1) This may be legacy code?
2) All three of these parameters, temperature, top_p and seed, are found in openai_payload["options"], not openai_payload. They do not need remapped any longer.
2025-02-19 08:44:59 -05:00
aea8977d05
Remove mapping of max_completion_tokens
...
1) max_completion_tokens is being looked for in openai_payload, but would be located in openai_payload['options'], so is never found. (This applies to the prior two commits as well).
2) max_completion_tokens is not sent from the frontend, only max_tokens. It does not appear in AdvancedParams.svelte.
2b) Openai.py does use max_completion_tokens, but for o1,o3 models and converts it from max_tokens.
2025-02-19 08:39:33 -05:00
e6919c3242
Remove mapping of frequency_penalty to repeat_penalty
...
1) Ollama natively supports frequency_penalty.
2) repeat_penaltywas added to Open Webui in PR #10016 and is not merged to main yet at this time. Once both changes go live, Ollama users can freely choose between frequency/presence penalty, or repeat penalty, as they choose.
2025-02-19 08:33:29 -05:00
a560f789e4
Remove mapping of presence_penalty to new_topix_penalty
...
1) Ollama natively supports presence_penalty.
2) new_topic_penalty is not a valid option in Ollama. (See https://github.com/ollama/ollama/blob/main/docs/api.md#request-8 )
3) Presence_penalty was added to Open Webui in PR #10016 and is not merged to main yet at this time.
2025-02-19 08:31:57 -05:00
61c6048b45
i18n: update zh-TW
2025-02-19 20:06:03 +08:00
1692a52a6a
fix(deps): upgrade pydantic from v2.9.2 to v2.10.3+ in requirements.txt and pyproject.toml
2025-02-19 19:08:17 +08:00
3e1337d753
Merge pull request #10341 from Youggls/dev
...
feat: Add Firecrawl web loader integration
2025-02-19 02:07:19 -08:00
0fb3c08181
feat: Add Firecrawl web loader integration
2025-02-19 16:54:44 +08:00
dab6396ebe
fix: inline citations
2025-02-19 00:35:01 -08:00
Timothy Jaeryang Baek