mirror of
https://github.com/Mintplex-Labs/anything-llm.git
synced 2026-07-19 14:13:35 -04:00
Closed
opened 2026-02-22 18:22:55 -05:00 by yindo
·
7 comments
No Branch/Tag Specified
master
5846-bug-when-scrolling-up-scrolling-jumps
refactor-remove-workspace-pfp
5969-bug-stopgenerationbutton-disappears-on-the-first-prompt-that-initiates-an-agent-session
2235-bug-how-to-upload-a-folder-with-subfolders-with-files-to-anythingllm
5990-workspace-update-fails-with-unknown-argument-router_id-v1130v1150-intel-mac
opencomputer-examples
pg
feat/image-generation-translations
feat/image-generation
5924-bug-meeting-summary-fails-with-sincludes-is-not-a-function-when-default-llm-is-anthropic-claude
render
feat/uniform-modal-component
5883-bug-unescaped-content-in-json-strings-being-passed-to-document-generator-tools
5901-bug-api-update-embeddings-fails-prisma-argument-filename-is-missing-on-workspace_documentscreate-desktop-windows-v1141
hybrid-search
1981-translations
5752-bug-prompts-to-local-jan-endpoint-unresponsive
feat-disable-native-tool-calling-env-var
5676-bug-non-ollama-agent-providers-do-not-parse-and-present-reasoning-content
feat/markdown-web-scraping
5717-bug-apiv1documentupload-silently-drops-metadata-field-in-desktop-1130-arg-count-mismatch-nested-payload-key
fix/aibitat-context-overflow
5711-bug-erratic-deepseek-v4-flash-the-agent-model-failed-to-respond-400-the-reasoning_content
5631-feat-custom-api-request-timeouts-for-ai-providers
feat-reasoning-control
feat-agent-clarifying-questions-translations
5583-bug-lm-studio-provider-does-not-present-reasoning-output
5313-normalize-translations
feat/memory-translations
5305-lemonade-embedding-engine-swallows-errors-falsely-reports-documents-as-embedded
5060-bug-agent-interactions-agent-are-not-persisted-to-thread-history-via-api
pptx-subagent
feat-render-images-from-mcp-tool-results
stt-provider-expansion-openai-api-compatible
feat-file-search-agent-tool
feat-native-embedder-job-queue
5189-normalize-translations
feat-file-search-agent-tool-translations
i18n-eslint
5140-auto-migration
5112-bug-openrouter-failed-message-bug
3506-feat-parameters-for-openrouter-models
4992-feat-preserve-scroll-position
4973-bug-markdown-numbered-list-display-in-reasoning-pane
desktop
4938-bug-pending-chat-rerendering-ui-bug
quickstart-env
node-llama-cpp-in-container-cuda
node-llama-cpp-in-container
ollama-in-container
4817-feat-set-cooldown-per-mcp-server
4845-keyboard-shortcuts-to-navigate-in-chat
4844-feat-reorder-threads-by-latest-interaction
standardize-username-constraints-normalize-translations
4792-feat-refactor-workspacepfp-image
1382-embed-ip-improvements
1382-bug-embed-api-improvements
refactor-eslint-frontend
4687-feat-refactor-vector-db-providers
4615-feat-disable-apidocs-with-environment-variable
4559-feat-agent-web-search-enable-ordering-of-results
4599-bug-ollama-race-condition-bug
4572-bug-lmstudio-provided-llm-stopped-working-with-anything-llm-after-upgrading-to-190
4508-agent-youtube-transcript-analysis
4497-feat-workspace-names
frontend-eslint
ollama-lmstudio-auto-context-window
4431-validate-vector-database-connectioN
2019-slash-command-keyboard-selection
microsoft-foundry-provider
4431-validate-vector-database-connection
4325-sys-prompt-var-improvements
3209-feat-apiv1workspacestream-chat-sources-citations
4210-bug-voice-to-text-overwrite
4136-feat-jan-as-a-backend-server-option
4172-feat-openai-o3-support
1.8.3-rerelease
web-push-notifications-service
tasks
3955-feat-jinaai-embedder-provider-support
3921-feat-agent-skills-uiux-improvements
3901-bug-validfunccall-checks-optional-arguments
keyboard-dev
1787-custom-roles-and-permissions
add-jira-slack-data-connector
office-extension-wip
lightmode-dropdown-color-update
3586-bug-agent-flow-function-description-provided-by-user-is-not-seen-in-the-llm-query
3463-bug-agent-continues-to-run-if-request-failed-even-after-exit
3439-feat-call-variables-within-the-flow-api-block-url-field
3282-manager-view-models-workspace
3280-token-counting-server-side-truncation-improvements
3147-bug-embedded-chat-widget---not-considering-query-mode-option-always-working-in-chat-mode
2995-feat-disable-temperature-setting-for-deepseek-r1-deepseek-reasoner-model
2827-feat-perplexity-citations
2866-feat-finally-a-gemini-models-endpoint
2647-feat-hpp-header-for-a-c++-code-file-mime-addition
lancedb-revert
1656-feat-implement-tooltip-ui-designs
2011-feat-bump-perplexity-models
1873-feat-auto-add-and-watch-folder-for-document-uploads
1297-feat-gemini-agent-support
1759-bug-ui-bug-fixes
1686-feat-implement-winston-for-logging
1536-bug-toggling-on-users-can-delete-workspaces-does-not-take-effect
agent-ui-mobile-styles
1522-feat-chromadb-support
1595-bug-unable-to-get-live-web-search-and-browsing-agent-working-using-google-custom-search-engine-error-getaddrinfo-enotfound-http-errno-3008
1582-bug-lm-studio-does-not-allow-for-different-model-selection
1312-bug-usernames-should-not-be-case-sensitive-when-logging-in
1029-feat-hf-serverless-inference-api
1086-feat-implement-normalized-input-fields
knowledge-graph-support
644-bug-uploaded-file-name-does-not-match-the-displayed-file-name-after-the-upload
v1.15.0
v1.14.2
v1.14.1
v1.14.0
v1.13.0
v1.12.1
v1.12.0
v1.11.2
v1.11.1
v1.11.0
v1.10.0
v1.9.1
v1.9.0
v1.8.5
v1.8.4
v1.8.3
v1.8.2
v1.8.1
v1.8.0
v1.7.8
v1.7.6
v1.7.5
v1.7.4
v1.4.0
v1.3.0
v1.2.4
v1.2.3
v1.2.2
v1.2.1
v1.2.0
v1.1.1
v1.1.0
v1.0.0
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
question
stage: specifications
wontfix
Mirrored from GitHub Pull Request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: Mintplex-Labs/anything-llm#1057
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @cyberlink1 on GitHub (Jun 6, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1627
How are you running AnythingLLM?
Docker (remote machine)
What happened?
Im working on getting anything-llm connected to n8n to process email requests.
The test workspace prompt includes the default plus "The body should be in a business email format . Output must be in JSON"
When I do the api call "/api/v1/workspace/xxxxxx/chat" to send it a message and get the response, the escaped CR and LF in the response are wrong. Sometimes it misses the escape before n or r sometimes it leaves off the n or r and sometimes it includes an \m.
Here is an example return I just pulled.
Just before "Best regards" you can see what I am talking about as there is an escape before the B in best, there should be an n there. There appear to be 3 such instances in the textResponse and it fails the json check.
Are there known steps to reproduce?
No response
@timothycarambat commented on GitHub (Jun 7, 2024):
This is because the file uploaded has the raw-text of
\n \r \tin it and when being JSONstringifiedthey are being properly escaped. What kind of file are you uploading that has this content in it?@cyberlink1 commented on GitHub (Jun 7, 2024):
I did not upload a file, I scraped a website for the information.
I find it had to believe that "\\Best Regards" is a proper escape.
@timothycarambat commented on GitHub (Jun 7, 2024):
Its clearly not, but what I am saying is that the content itself has a literal
\in it, so it's being escaped. What is the link?The raw content is coming across as
\Best Regards- why there is a slash, I'm not sure. All we do isJSON.Stringifyso we do no additional parsing on top of that@cyberlink1 commented on GitHub (Jun 7, 2024):
That is an AI generated email salutation. It is not part of anything scraped. I scraped a company called vizientinc to load the data for testing. Something to do with healthcare and was a decent size. I scraped 3 deep and 20 links.
@timothycarambat commented on GitHub (Jun 7, 2024):
@cyberlink1 I apologize, this entire time I thought we had been talking about content scraped from a website not a response. I just got off a long flight back from China so I'm still jet lagged.
Okay, so the response from the LLM somehow resulted in a
\\Best Regardsin the response. Which is indeed weird. What model are you using for chatting?So with
textResponsewe simply save the output - we don't apply any type of processing on it. LLMs are surprisingly bad at generating reliable JSON output. Its a persistent problem and I simply think all that occurred here is a hallucination. That is it!Here is what we do to try to alleviate bad JSON hallucinations since LLMs, especially OSS LLMs, are horrendous at just making decent JSON and most provides don't have a JSON mode that just works.
https://github.com/Mintplex-Labs/anything-llm/blob/3434bf4686901721b109b7d67b771ef2957f264c/server/utils/http/index.js#L66
Feel free to borrow that function. In fact, when i use it on your output it gets a better result:
@cyberlink1 commented on GitHub (Jun 7, 2024):
No worries, I know how jetlag can be.
Im using ollama with minstrel as the llm. I tested the backend ollama and the escapes were not in the response, I then tested from anythingllm and found the escapes. Trying to narrow down where they were being injected.
Ill see what I can do with the function, Im not well versed in java.
@timothycarambat commented on GitHub (Jun 7, 2024):
They for sure came from the LLM result directly. Since LLMs are non-deterministic you'll probably get a slightly different result every time even when using Ollama directly or via AnythingLLM. Makes solving the problem even harder since you might get good JSON directly 8/10 times, but the other 2 times are close but not strictly valid so they need to be attempted to be repaired and if that fails - assume the response is text.
In your case, since you just want JSON and nothing else you can attempt to parse/repair the response and if its not JSON - exit the function early.
[BUG]: API json output messing up escaped CR and LFto [GH-ISSUE #1627] [BUG]: API json output messing up escaped CR and LF