4032 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
-LAN-	02c39b2631	fix(file-uploader): resolve file extension logic order ... Rearranged the logic in `getFileExtension` to first check for a valid `fileName` before considering `fileMimetype` or `isRemote`. This change ensures that the function prioritizes extracting extensions from file names directly, improving accuracy and handling edge cases more effectively. This update may prevent incorrect file extensions when mimetype is prioritized incorrectly. Resolves #123.	2024-11-15 11:51:56 +08:00
-LAN-	87f78ff582	feat: enhance image handling in prompt processing ... Updated image processing logic to check for model support of vision features, preventing errors when handling images with models that do not support them. Added a test scenario to validate behavior when vision features are absent. This ensures robust image handling and avoids unexpected behavior during image-related prompts.	2024-11-15 11:51:56 +08:00
-LAN-	6872b32c7d	fix(node): handle empty text segments gracefully ... Ensure that messages are only created from non-empty text segments, preventing potential issues with empty content. test: add scenario for file variable handling Introduce a test case for scenarios involving prompt templates with file variables, particularly images, to improve reliability and test coverage. Updated `LLMNodeTestScenario` to use `Sequence` and `Mapping` for more flexible configurations. Closes #123, relates to #456.	2024-11-15 11:51:56 +08:00
-LAN-	97fab7649b	feat(tests): refactor LLMNode tests for clarity ... Refactor test scenarios in LLMNode unit tests by introducing a new `LLMNodeTestScenario` class to enhance readability and consistency. This change simplifies the test case management by encapsulating scenario data and reduces redundancy in specifying test configurations. Improves test clarity and maintainability by using a structured approach.	2024-11-15 11:51:56 +08:00
-LAN-	9f0f82cb1c	refactor(tests): streamline LLM node prompt message tests ... Refactored LLM node tests to enhance clarity and maintainability by creating test scenarios for different file input combinations. This restructuring replaces repetitive code with a more concise approach, improving test coverage and readability. No functional code changes were made. References: #123, #456	2024-11-15 11:51:56 +08:00
-LAN-	ef08abafdf	Simplify test setup in LLM node tests ... Replaced redundant variables in test setup to streamline and align usage of fake data, enhancing readability and maintainability. Adjusted image URL variables to utilize consistent references, ensuring uniformity across test configurations. Also, corrected context variable naming for clarity. No functional impact, purely a refactor for code clarity.	2024-11-15 11:51:56 +08:00
-LAN-	d6c9ab8554	feat(llm_node): allow to use image file directly in the prompt.	2024-11-15 11:51:56 +08:00
-LAN-	bab989e3b3	Remove unnecessary data from log and text properties ... Updated the log and text properties in segments to return empty strings instead of the segment value. This change prevents potential leakage of sensitive data by ensuring only non-sensitive information is logged or transformed into text. Addresses potential security and privacy concerns.	2024-11-15 11:51:56 +08:00
-LAN-	ddc86503dc	refactor(model_manager): update parameter type for flexibility ... - Changed 'prompt_messages' parameter from list to Sequence for broader input type compatibility.	2024-11-15 11:51:56 +08:00
-LAN-	abad35f700	refactor(memory): use Sequence instead of list for prompt messages ... - Improved flexibility by using Sequence instead of list, allowing for broader compatibility with different types of sequences. - Helps future-proof the method signature by leveraging the more generic Sequence type.	2024-11-15 11:51:56 +08:00
-LAN-	620b0e69f5	fix(dependencies): update Faker version constraint ... - Changed the Faker version from caret constraint to tilde constraint for compatibility. - Updated poetry.lock for changes in pyproject.toml content.	2024-11-15 11:51:56 +08:00
-LAN-	71cf4c7dbf	chore(config): remove unnecessary 'frozen' parameter for test ... - Simplified app configuration by removing the 'frozen' parameter since it is no longer needed. - Ensures more flexible handling of config attributes.	2024-11-15 11:51:20 +08:00
-LAN-	47e8a5d4d1	refactor(model_runtime): use Sequence for content in PromptMessage ... - Replaced list with Sequence for more flexible content type. - Improved type consistency by importing from collections.abc.	2024-11-15 11:51:20 +08:00
-LAN-	93bbb194f2	refactor(prompt): enhance type flexibility for prompt messages ... - Changed input type from list to Sequence for prompt messages to allow more flexible input types. - Improved compatibility with functions expecting different iterable types.	2024-11-15 11:51:20 +08:00
-LAN-	2106fc5266	fix(tests): update Azure Rerank Model usage and clean imports	2024-11-15 11:51:20 +08:00
-LAN-	229b146525	feat(errors): add new error classes for unsupported prompt types and memory role prefix requirements	2024-11-15 11:51:20 +08:00
-LAN-	d9fa6f79be	refactor: update jinja2_variables and prompt_config to use Sequence and add validators for None handling	2024-11-15 11:51:20 +08:00
-LAN-	4f89214d89	refactor: update stop parameter type to use Sequence instead of list	2024-11-15 11:51:20 +08:00
-LAN-	1fdaea29aa	refactor(converter): simplify model credentials validation logic	2024-11-15 11:51:20 +08:00
-LAN-	1397d0000d	chore(deps): add faker	2024-11-15 11:51:20 +08:00
非法操作	4b2abf8ac2	fix: create_blob_message of tool will always create image type file (#10701)	2024-11-15 10:38:12 +08:00
Bowen Liang	365cb4b368	chore(lint): bump ruff from 0.6.9 to 0.7.3 (#10714)	2024-11-15 09:19:41 +08:00
GeorgeCaoJ	c85bff235d	fix(i18n): handle key naming error (#10713)	2024-11-15 09:01:38 +08:00
Kalo Chin	ad16180b1a	feat(tool): fal ai wizper ASR built-in tool (#10716)	2024-11-15 09:01:07 +08:00
jarvis2f	5ff02b469f	fix:position error when creating segments (#10706)	2024-11-14 21:25:15 +08:00
Bowen Liang	44f57ad9a8	chore: Bump Alpine Linux to 3.20 in web dockerfile (#10671)	2024-11-14 20:57:01 +08:00
yihong	94fd6f6901	fix: typo in test (#10707) ... Signed-off-by: yihong0618 <zouzou0208@gmail.com>	2024-11-14 20:54:13 +08:00
SiliconFlow, Inc	e61242a337	feat: add vlm models from siliconflow (#10704)	2024-11-14 20:53:35 +08:00
yihong	722964667f	fix: non utf8 code decode close #10691 (#10698) ... Signed-off-by: yihong0618 <zouzou0208@gmail.com>	2024-11-14 17:29:49 +08:00
Xiao Ley	fbb9c1c249	fixed the Base URL usage issue in Podcast Generator tool verification (#10697)	2024-11-14 17:24:42 +08:00
非法操作	15f341b655	feat: add the audio tool (#10695)	2024-11-14 16:37:15 +08:00
crazywoola	b358490607	chore: update issue template (#10693)	2024-11-14 16:12:27 +08:00
crazywoola	f9e4196fd5	Update pull_request_template.md (#10692)	2024-11-14 15:56:37 +08:00
crazywoola	751525802d	feat: update pr template (#10690)	2024-11-14 15:52:15 +08:00
lz	2abacd2a2d	export configuration 'CODE_EXECUTION_TIMEOUT' to .env (#10688) ... Co-authored-by: liuzhu <liuzhu@fridaycloud.com.cn>	2024-11-14 15:34:34 +08:00
Nam Vu	a3155e0613	Update expat version (#10686)	2024-11-14 15:30:55 +08:00
Jyong	70b9e4caf5	check dataset is none (#10682)	2024-11-14 14:07:19 +08:00
orangeclk	317ae9233e	feat: add json response format for siliconflow models (#10657)	2024-11-14 08:58:22 +08:00
xiandan-erizo	5b8f03cd9d	add abab7-chat-preview model (#10654) ... Co-authored-by: xiandan-erizo <xiandan-erizo@outlook.com>	2024-11-13 19:30:42 +08:00
Kalo Chin	2a4783307a	Feat(tool): fal ai flux image generation (#10606)	2024-11-13 17:41:58 +08:00
非法操作	bddecba9ed	fix: mp3 file upload not work (#10650)	2024-11-13 17:37:29 +08:00
jiangbo721	931e76e3d1	fix: remove unused queue generation (#10532) ... Co-authored-by: 刘江波 <jiangbo721@163.com>	2024-11-13 15:52:52 +08:00
-LAN-	70c2ec8ed5	feat(variable-handling): enhance variable and segment conversion (#10483)	2024-11-12 21:51:09 +08:00
wakaka6	9c7edb9242	feat: add builtin tools for send email (#10493)	2024-11-12 21:48:36 +08:00
Benjamin	0867821ae7	fix: update conversation session naming and API path in documentation (#10589)	2024-11-12 21:44:04 +08:00
Jyong	0b2d51d859	add the index field for elasticsearch (#10592)	2024-11-12 21:43:16 +08:00
方程	ef8022f715	Gitee AI Qwen2.5-72B model (#10595)	2024-11-12 21:40:32 +08:00
Kevin9703	e03ec0032b	fix: Azure OpenAI o1 max_completion_token error (#10593)	2024-11-12 21:40:13 +08:00
dependabot[bot]	62642443ef	chore(deps): bump elliptic from 6.5.7 to 6.6.0 in /web (#10587) ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-11-12 16:43:11 +08:00
-LAN-	3e04c92ff9	chore(api): remove setting of expired remember_token cookie in after_request (#10582)	2024-11-12 15:53:55 +08:00