3046 Commits

Author SHA1 Message Date
ferret99gt
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
ferret99gt
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
ferret99gt
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
ferret99gt
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
ferret99gt
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
ferret99gt
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
ferret99gt
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
ferret99gt
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
ferret99gt
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
ferret99gt
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
Youggls
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
Youggls
0fb3c08181 feat: Add Firecrawl web loader integration 2025-02-19 16:54:44 +08:00
Timothy Jaeryang Baek
c073b8b4ee refac 2025-02-18 23:49:27 -08:00
Timothy Jaeryang Baek
9ca4727573 enh: web search behaviour 2025-02-18 21:29:27 -08:00
Timothy Jaeryang Baek
5465cabd40 refac 2025-02-18 21:17:09 -08:00
Timothy Jaeryang Baek
81715f6553 enh: RAG full context mode 2025-02-18 21:14:58 -08:00
Timothy Jaeryang Baek
1bbecd46c8
Merge pull request #10052 from roryeckel/playwright
Support Playwright RAG Web Loader: Revised
2025-02-18 19:57:48 -08:00
Timothy Jaeryang Baek
4ef7aff663 refac 2025-02-18 19:35:22 -08:00
Timothy Jaeryang Baek
8f7528a0bc
Merge pull request #10272 from mkhludnev/dedupe-rag-docs
fix: dedupe results from multiple queries
2025-02-18 19:34:33 -08:00
Timothy Jaeryang Baek
5a7f9c81e3
Merge pull request #10308 from crpietschmann/azure-storage
feat: Add AzureStorageProvider for Azure Blob Storage support
2025-02-18 19:32:17 -08:00
Timothy Jaeryang Baek
886d756200
Merge pull request #10285 from the-c0d3br34k3r/issue8885_auth
fix: Fixed an issue with clearing application cookies during OAuth signout
2025-02-18 19:31:24 -08:00
Timothy Jaeryang Baek
32a90deeaf
Merge pull request #10309 from JoaoCostaIFG/gemini_image_gen
feat: add Google Imagen/Gemini API image generation
2025-02-18 19:30:20 -08:00
JoaoCostaIFG
918764a4f7
fix: Use x-goog-api-key header for Gemini image generation
Place the API key in a header instead of a query parameter. This avoids leaking the API key in logs on request failure, etc...
2025-02-19 00:00:54 +00:00
JoaoCostaIFG
e56b5c063c
feat: add Google Imagen/Gemini API image generation
Adds support for Gemini API as an image generation backend. By setting the API Base URL to something like 'https://generativelanguage.googleapis.com/v1beta' and providing their API Key, users should be able to start generating images using models like 'imagen-3.0-generate-002'.
2025-02-18 22:39:32 +00:00
Chris Pietschmann
a232f1f34e Update test_provider.py 2025-02-18 15:53:54 -05:00
Chris Pietschmann
9864185b57 Update test_provider.py 2025-02-18 15:49:44 -05:00
Chris Pietschmann
888ae00867 Update test_provider.py 2025-02-18 15:39:47 -05:00
Chris Pietschmann
7b5f82ffc7 Update test_provider.py 2025-02-18 15:26:04 -05:00
Chris Pietschmann
7404494772 formatting 2025-02-18 15:19:35 -05:00
Chris Pietschmann
a29f83c4e7 updates to formatting 2025-02-18 15:17:49 -05:00
Chris Pietschmann
4c352ff974 Update test_provider.py 2025-02-18 15:14:46 -05:00
Chris Pietschmann
55bd7a1c65 Update test_provider.py 2025-02-18 15:13:30 -05:00
Chris Pietschmann
9c8c837ab9 Update test_provider.py 2025-02-18 15:12:35 -05:00
Chris Pietschmann
2c328cc7c9 Update test_provider.py 2025-02-18 15:04:49 -05:00
Chris Pietschmann
56060db29d Update test_provider.py 2025-02-18 15:01:26 -05:00
Chris Pietschmann
7d1ec20429 Update test_provider.py 2025-02-18 14:57:51 -05:00
Chris Pietschmann
ff5f0c3e39 Update test_provider.py 2025-02-18 14:51:17 -05:00
Chris Pietschmann
9a2e81f5f0 Update test_provider.py 2025-02-18 14:49:03 -05:00
Chris Pietschmann
f674e28263 Update test_provider.py 2025-02-18 14:45:13 -05:00
Chris Pietschmann
4a9a88b683 Update test_provider.py 2025-02-18 14:41:42 -05:00
Chris Pietschmann
b86f8df29f Update test_provider.py 2025-02-18 14:37:10 -05:00
Chris Pietschmann
2f4f4c2376 add tests 2025-02-18 14:09:00 -05:00
Chris Pietschmann
745b24f13a
Merge branch 'open-webui:main' into azure-storage 2025-02-18 13:36:56 -05:00
Chris Pietschmann
aee57107bc Update config.py 2025-02-18 13:27:37 -05:00
Chris Pietschmann
e4febfa097 Add AzureStorageProvider config options 2025-02-18 13:25:49 -05:00
Chris Pietschmann
fd3c24af4e Add AzureStorageProvider 2025-02-18 13:25:31 -05:00
Timothy Jaeryang Baek
d0114e0703 fix: temp chat issue 2025-02-18 09:57:12 -08:00
Ranjan Mohan
6c6be5de88 Fixed an issue with clearing application cookies during OAuth signout
Closes #8885.

During the OAuth signout flow, although the `token` and `oauth_id_token`
cookies were marked for deletion, a new RedirectResponse is created and
returned. This does not contain the header info from the he Response object
used to mark the cookies to be deleted. Hence the cookies remained.
Fixed this by re-using the headers from the other Response object.
2025-02-18 12:44:14 -05:00
mikhail-khludnev
925bfe840b dedupe results from multiple queries 2025-02-18 20:10:57 +03:00
Timothy Jaeryang Baek
1764170307 refac 2025-02-17 21:34:06 -08:00