1808837298@qq.com
71682f1522
fix: Update Claude thinking adapter token percentage input guidance
2025-02-27 20:59:32 +08:00
1808837298@qq.com
ed1a1c9b09
fix: Correct model request configuration in Vertex Claude adaptor
2025-02-27 20:51:10 +08:00
1808837298@qq.com
5371af0b42
feat: Refactor model configuration management with new config system
...
- Introduce a new configuration management approach for model-specific settings
- Update Gemini settings to use the new config system with more flexible management
- Add support for dynamic configuration updates in option handling
- Modify Claude and Vertex adaptors to use new configuration methods
- Enhance web interface to support namespaced configuration keys
2025-02-27 20:49:34 +08:00
1808837298@qq.com
fd6ae3ea78
feat: Add Claude model configuration management #791
2025-02-27 20:49:21 +08:00
1808837298@qq.com
fe9a3025d1
fix: Add pagination support to user search functionality
2025-02-27 16:55:02 +08:00
1808837298@qq.com
bf9f5e59b5
chore: Update Azure OpenAI API version and embedding model detection
...
- Enhance channel test to detect more embedding models
- Update Azure OpenAI default API version to 2024-12-01-preview
- Remove redundant default API version setting in channel edit
- Add user cache writing in channel test
2025-02-27 16:49:32 +08:00
1808837298@qq.com
2d77733cd3
fix: Improve AWS Claude adaptor request conversion error handling #796
2025-02-27 14:57:00 +08:00
1808837298@qq.com
ac00e9bbb3
init openrouter adaptor
2025-02-27 00:01:21 +08:00
1808837298@qq.com
0646fa1892
fix: gemini&claude tool call format #795 #766
2025-02-26 23:56:10 +08:00
1808837298@qq.com
23de62ec0d
fix: claude tool call format #795 #766
2025-02-26 23:40:16 +08:00
1808837298@qq.com
c3b0e57ea4
feat: Add Jina reranking support for OpenAI adaptor
2025-02-26 21:46:06 +08:00
1808837298@qq.com
ce03e77906
fix: Update Gemini safety settings to use 'OFF' as default
2025-02-26 19:20:17 +08:00
1808837298@qq.com
832f4b2b1a
fix: Update Gemini safety settings category
2025-02-26 19:18:00 +08:00
1808837298@qq.com
7100c787d4
fix: Update Gemini safety settings default value
2025-02-26 19:01:45 +08:00
1808837298@qq.com
8a30d64a75
feat: Add Gemini version settings configuration support ( close #568 )
2025-02-26 18:19:09 +08:00
1808837298@qq.com
0a369cc193
feat: Add Gemini safety settings configuration support ( close #703 )
2025-02-26 16:54:43 +08:00
1808837298@qq.com
5ba44f5ad5
feat: Update Claude relay temperature setting
2025-02-25 22:01:05 +08:00
1808837298@qq.com
d04d78a116
refactor: Enhance user context and quota management
...
- Add new context keys for user-related information
- Modify user cache and authentication middleware to populate context
- Refactor quota and notification services to use context-based user data
- Remove redundant database queries by leveraging context information
- Update various components to use new context-based user retrieval methods
2025-02-25 20:56:16 +08:00
1808837298@qq.com
8c2323d74d
feat: redis poolsize
2025-02-25 19:39:29 +08:00
1808837298@qq.com
583678d9ff
fix: Adjust Claude thinking mode request parameters
2025-02-25 16:52:45 +08:00
1808837298@qq.com
fd38e59f78
docs: Update README
2025-02-25 16:31:42 +08:00
1808837298@qq.com
d4706d6b8e
Merge branch 'main' into thinking
...
# Conflicts:
# relay/channel/claude/dto.go
2025-02-25 15:21:22 +08:00
1808837298@qq.com
6c8016e5f8
feat: Add support for Claude thinking parameter in request
2025-02-25 14:37:03 +08:00
1808837298@qq.com
c62276fcc4
feat: Add Claude 3.7 Sonnet model to AWS channel mapping
2025-02-25 02:55:23 +08:00
1808837298@qq.com
15a3b44689
feat: Add support for Claude 3.7 Sonnet model
2025-02-25 02:51:31 +08:00
1808837298@qq.com
8f3c7280cf
feat: Support max_tokens parameter for Ollama channel #782
2025-02-24 17:35:49 +08:00
1808837298@qq.com
6f3072895a
feat: Add model rate limit settings in system configuration
2025-02-24 16:27:20 +08:00
1808837298@qq.com
1763145fea
feat: Add model request rate limiting functionality
2025-02-24 16:20:55 +08:00
1808837298@qq.com
66831a1bde
feat: Add support for different Dify bot types and request URLs
2025-02-24 14:18:30 +08:00
1808837298@qq.com
fd44ac7c0c
feat: Enhance token counting and content parsing for messages
2025-02-24 14:18:15 +08:00
1808837298@qq.com
7becf62a7a
fix: Improve 429 error logging with detailed message
2025-02-23 21:26:31 +08:00
1808837298@qq.com
40c0333eaa
fix typo
2025-02-23 17:27:33 +08:00
1808837298@qq.com
65021e2e0e
feat: Add thinking-to-content option in channel extra settings #780
2025-02-23 17:13:08 +08:00
1808837298@qq.com
4597816a14
feat: Add thinking-to-content conversion for stream responses
2025-02-23 17:05:57 +08:00
1808837298@qq.com
991b6f8bb0
fix: mistral
2025-02-22 16:29:48 +08:00
1808837298@qq.com
0333576bee
fix: fix image ratio calculation
2025-02-22 15:50:18 +08:00
1808837298@qq.com
7a13f9c99a
fix: Ensure correct quota warning threshold type conversion
2025-02-22 15:19:55 +08:00
1808837298@qq.com
1c20d16c49
chore: update rerank.md
2025-02-22 15:13:26 +08:00
1808837298@qq.com
3eb186825d
fix: ShouldDisableChannel
2025-02-22 02:02:03 +08:00
1808837298@qq.com
d71315cfa5
fix: mistral adaptor ( close #774 )
2025-02-21 22:21:19 +08:00
1808837298@qq.com
8101cd3ce3
feat: Add reasoning content support in OpenAI response handling
2025-02-21 18:52:51 +08:00
1808837298@qq.com
4a49d6c795
refactor: Improve message content parsing with robust type handling
2025-02-21 18:27:43 +08:00
1808837298@qq.com
4194f4bd21
refactor: Improve message content handling and quota error responses
2025-02-21 18:18:21 +08:00
1808837298@qq.com
e1784f8981
refactor: Optimize sensitive word detection and text processing
2025-02-21 17:05:35 +08:00
1808837298@qq.com
78f9a30c39
feat: Enhance sensitive word detection with detailed logging
2025-02-21 16:57:30 +08:00
1808837298@qq.com
009333da8b
refactor: Improve quota error messages with formatted quota display
2025-02-21 16:42:48 +08:00
1808837298@qq.com
23bfc06fd8
feat: Add base URL input with localized tooltip for channel configuration
2025-02-21 16:17:59 +08:00
1808837298@qq.com
f64540cd1c
feat: Add localization for notification and webhook settings
2025-02-21 15:36:24 +08:00
1808837298@qq.com
1e0b414fc0
refactor: Simplify model mapping and pricing logic across relay modules
2025-02-20 16:41:46 +08:00
1808837298@qq.com
8dbac87e92
fix: Correct Ollama channel authentication header setting
2025-02-20 01:28:15 +08:00
CalciumIon
1f6cb4bd5d
feat: Improve mobile text truncation and sidebar visibility
2025-02-19 23:25:42 +08:00
1808837298@qq.com
5ef44f6898
feat: Improve image handling for Ollama channels
2025-02-19 20:45:42 +08:00
1808837298@qq.com
604a5b1ad5
feat: Enhance Ollama channel support with additional request parameters #771
2025-02-19 19:58:34 +08:00
1808837298@qq.com
cc61f85bdd
fix: Remove redundant error handling in distributor and relay modules
2025-02-19 18:47:28 +08:00
1808837298@qq.com
4ea2556b29
refactor: Replace manual goroutine creation with gopool.Go
2025-02-19 18:38:29 +08:00
1808837298@qq.com
8a34d61654
chore: update env name and README
2025-02-19 15:54:33 +08:00
1808837298@qq.com
67f02e0a6a
docs: Add proxy usage information note in SystemSetting component
2025-02-19 15:45:09 +08:00
1808837298@qq.com
097d02eb8b
feat: Implement comprehensive webhook notification system
2025-02-19 15:40:54 +08:00
1808837298@qq.com
1ae0a38485
refactor: Optimize user caching and token retrieval methods
2025-02-19 15:12:26 +08:00
1808837298@qq.com
af9d03140c
fix: Extend temperature handling for OpenAI-like models
...
- Add support for suppressing temperature for o1 models
- Expand model prefix check to include 'o1' alongside 'o3' models
2025-02-18 16:00:56 +08:00
1808837298@qq.com
83e161a1d4
refactor: Simplify root user notification and remove global email variable
...
- Remove global `RootUserEmail` variable
- Modify channel testing and user notification methods to use `GetRootUser()`
- Update user cache and notification service to use more consistent user base type
- Add new channel test notification type
2025-02-18 15:59:17 +08:00
1808837298@qq.com
9a41c04416
feat: Implement notification rate limiting mechanism
...
- Add in-memory and Redis-based notification rate limiting
- Create configurable hourly notification limits
- Implement notification limit checking for user notifications
- Add environment variables for customizing notification limits
2025-02-18 15:30:43 +08:00
1808837298@qq.com
e0ce8bf2b3
refactor: Improve CompletionRatio handling with thread-safe access and initialization
2025-02-18 15:01:43 +08:00
1808837298@qq.com
0fcd243f56
feat: Add user notification settings with quota warning and multiple notification methods
...
- Implement user notification settings with email and webhook options
- Add new user settings for quota warning threshold and notification preferences
- Create backend API and database support for user notification configuration
- Enhance frontend personal settings with notification configuration UI
- Support custom notification email and webhook URL
- Add service layer for sending user notifications
2025-02-18 14:54:21 +08:00
1808837298@qq.com
a353ea3eee
Merge remote-tracking branch 'origin/main'
2025-02-17 18:15:13 +08:00
1808837298@qq.com
1cfe06c3d8
feat: Add support for DeepSeek completions endpoint
2025-02-17 18:15:01 +08:00
1808837298@qq.com
65faa158b6
refactor: Optimize channel testing and model menu generation ( fix #761 )
2025-02-15 19:12:28 +08:00
1808837298@qq.com
d43c5d6003
refactor: Improve channel property update mechanism ( fix #761 )
2025-02-15 15:30:55 +08:00
1808837298@qq.com
2869dbf60a
feat: Enhance VolcEngine channel support with bot model routing ( fix #757 )
2025-02-15 00:10:58 +08:00
1808837298@qq.com
9e2433e2a6
fix: Improve OpenAI stream data parsing and handling
2025-02-14 23:52:25 +08:00
1808837298@qq.com
025b6d1226
feat: Add automatic channel disabling based on configurable keywords
...
- Introduce AutomaticDisableKeywords setting to dynamically control channel disabling
- Implement AC search for matching error messages against disable keywords
- Add frontend UI for configuring automatic disable keywords
- Update localization with new keyword-based channel disabling feature
- Refactor sensitive word and AC search logic to support multiple keyword lists
2025-02-13 16:39:17 +08:00
1808837298@qq.com
5665b1a58b
refactor: Optimize log retrieval with separate channel name fetching ( fix #751 )
...
- Remove inline channel join in log queries
- Implement separate channel name lookup for logs
- Improve performance by fetching channel names in a single query
- Ensure channel names are correctly associated with logs
2025-02-12 19:19:13 +08:00
1808837298@qq.com
ed888fb717
feat: Add invite link banner for specific channel type
2025-02-12 17:48:48 +08:00
1808837298@qq.com
e84d602e17
refactor: Optimize Dockerfile for Go build process
...
- Use alpine-based Golang image for smaller build size
- Simplify Go build command by removing static linking flag
- Improve Docker multi-stage build configuration
2025-02-12 17:18:23 +08:00
1808837298@qq.com
cc5e683784
docs: Update README with detailed Docker deployment and update instructions
2025-02-12 16:54:53 +08:00
1808837298@qq.com
6fe7b15cd0
fix: Update BaseURL placeholder text and label in channel edit page
2025-02-12 15:39:18 +08:00
1808837298@qq.com
61ad1adbda
feat: Improve embedding request handling and support across channels
...
- Update EmbeddingRequest DTO to support more flexible input types
- Add input parsing method to handle various input formats
- Implement ConvertEmbeddingRequest for multiple channel adaptors
- Remove relayMode parameter from EmbeddingHelper
- Add input validation for embedding requests
- Simplify embedding request conversion for different channels
2025-02-12 14:39:36 +08:00
1808837298@qq.com
babbbfb346
feat: Add Baidu Qianfan V2 channel support #725
...
- Update channel constants to include Baidu V2 channel
- Create new Baidu V2 adaptor for relay
- Add Baidu V2 models and channel configuration
- Update relay adaptor to support Baidu V2 channel
- Modify web channel constants to include Baidu V2 option
2025-02-12 00:07:02 +08:00
1808837298@qq.com
4d6bce1ddd
feat: Add support for VolcEngine (Doubao) channel #313 #734
2025-02-11 23:47:15 +08:00
1808837298@qq.com
86d93c4694
fix: adjust max tokens configuration in test request builder
...
- Update max tokens default value to 10
2025-02-11 20:00:05 +08:00
1808837298@qq.com
93511cfbf9
feat: enhance OpenAI request and response DTOs
...
- Add `Prefix` and `ReasoningContent` fields to Message struct
- Add getter and setter methods for `Prefix`
- Make `ToolCall.ID` field optional (fix #749 )
2025-02-11 19:54:54 +08:00
1808837298@qq.com
305be19bb2
chore: disable cgo
2025-02-11 18:51:27 +08:00
1808837298@qq.com
cb458caefd
chore: disable cgo
2025-02-11 18:51:09 +08:00
1808837298@qq.com
0be6c5ee69
chore: replace sqlite lib with prue go lib
2025-02-11 18:34:34 +08:00
1808837298@qq.com
51b13ce038
chore: update CI
2025-02-11 18:23:20 +08:00
1808837298@qq.com
0486041952
update CI
2025-02-11 17:44:54 +08:00
1808837298@qq.com
8f3752c423
feat: enhance session store security and configuration
...
- Add 30-day max age for session cookies
- Enable HttpOnly flag
- Set SameSite to strict mode
2025-02-11 17:06:51 +08:00
1808837298@qq.com
94c10d8def
fix: update session store configuration
...
- Change session cookie path from "/api" to "/"
- Remove HttpOnly flag
2025-02-11 15:53:15 +08:00
1808837298@qq.com
6a9c0fd2c0
feat: configure session store options for API routes
...
- Set session cookie path to "/api"
- Disable secure flag for local development
- Enable HttpOnly flag for improved security
2025-02-11 15:45:24 +08:00
1808837298@qq.com
d4855da092
chore: update CI
2025-02-11 13:14:38 +08:00
1808837298@qq.com
147d0f211b
chore: update CI
2025-02-10 21:59:41 +08:00
1808837298@qq.com
6d021b20b7
fix: replace context-based user ID with session-based retrieval #741
...
- Update user and wechat controllers to use sessions for user ID
- Modify ID retrieval to use `session.Get("id")` instead of `c.GetInt("id")`
- Cast session ID to int when creating user object
2025-02-10 20:52:33 +08:00
1808837298@qq.com
e65238a327
fix: CI #744
2025-02-10 20:39:04 +08:00
1808837298@qq.com
451d23a129
Merge remote-tracking branch 'origin/main'
2025-02-10 20:34:11 +08:00
1808837298@qq.com
bb1358ca47
refactor: improve SSE response handling in Playground
...
- Simplify event listener logic for streaming responses
- Add null-safe checks for payload content
- Optimize message generation and completion flow
2025-02-10 20:24:14 +08:00
1808837298@qq.com
276f9991c5
fix: channels model_mapping
2025-02-06 19:51:33 +08:00
1808837298@qq.com
df848c3a1b
fix: update logs table total count display
...
- Replace `logs.length` with `logCount` in pagination information
- Ensure accurate total log count is displayed in the logs table
2025-02-06 14:56:23 +08:00
1808837298@qq.com
c8a8526ff3
feat: modify channel model_mapping column type to TEXT
...
- Change `ModelMapping` column type from varchar(1024) to TEXT in channels table
- Add MySQL migration script to alter column type during database initialization
- Improve database schema flexibility for storing complex model mappings
2025-02-06 14:35:14 +08:00
1808837298@qq.com
906516fb90
feat: add SOCKS5 proxy authentication support
...
- Enhance `NewProxyHttpClient` to handle SOCKS5 proxy authentication
- Extract username and password from proxy URL for SOCKS5 proxy configuration
- Provide optional authentication for SOCKS5 proxy connections
2025-02-04 18:10:25 +08:00
1808837298@qq.com
881be9a3ec
feat: add demo site configuration flag
...
- Introduce `DemoSiteEnabled` variable in operation settings
- Provide a configurable flag to enable/disable demo site functionality
2025-02-04 14:15:01 +08:00
1808837298@qq.com