I have searched for any existing and/or related issues.
I have searched for any existing and/or related discussions.
I am using the latest version of Open WebUI.
Installation Method
Git Clone
Open WebUI Version
6.30
Ollama Version (if applicable)
Mistral 7-b
Operating System
Ubuntu
Browser (if applicable)
No response
Confirmation
I have read and followed all instructions in README.md.
I am using the latest version of both Open WebUI and Ollama.
I have included the browser console logs.
I have included the Docker container logs.
I have provided every relevant configuration, setting, and environment variable used in my setup.
I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
Start with the initial platform/version/OS and dependencies used,
Specify exact install/launch/configure commands,
List URLs visited, user input (incl. example values/emails/passwords if needed),
Describe all options and toggles enabled or changed,
Include any files or environmental changes,
Identify the expected and actual result at each stage,
Ensure any reasonably skilled user can follow and hit the same issue.
Expected Behavior
Expected Behavior:
When I upload or input my resume into OpenWebUI, the system should correctly read and parse all the content, accurately identifying sections such as work experience, education, and skills, without misplacing or omitting any information.
Description:
When uploading a resume PDF into OpenWebUI, the document analysis summary returned incorrect details that do not exist in the file. For example, the system output mentioned roles at ABC Corporation and XYZ Company, and degrees from University of Michigan and Stanford University, which were not part of the uploaded resume.
This indicates that the document parsing or summarisation function is either hallucinating content or not reading the PDF correctly.
Actual Behavior
Expected Behavior:
When I upload or input my resume into OpenWebUI, the system should correctly read and parse all the content, accurately identifying sections such as work experience, education, and skills, without misplacing or omitting any information.
Steps to Reproduce
Steps to Reproduce:
Open OpenWebUI.
Upload a resume PDF (example attached: Abhi Chaturvedi.pdf).
Run the "summarise the resume" prompt.
Observe that the output contains fabricated details not present in the actual resume.
Expected Result:
The system should accurately summarise the uploaded resume contents without fabricating details.
Actual Result:
The system generated a summary with companies, universities, and job details that were not present in the PDF.
Impact:
Incorrect parsing reduces reliability of OpenWebUI’s document analysis features and can mislead users relying on accurate summaries.
Attachments:
Example screenshot of wrong output
Original PDF used for testing
Logs & Screenshots
Additional Information
Additional Details:
Resume Format: The document uploaded is in [specify format, e.g., PDF, DOCX].
Issue Observed: OpenWebUI incorrectly reads the resume content, misplacing or omitting sections such as work experience, education, or skills.
Steps to Reproduce:
Open OpenWebUI.
Upload or paste the resume document.
Observe the parsed output; sections do not match the original content.
Environment Details:
OpenWebUI version: [specify version if known]
Operating System: [e.g., Ubuntu 22.04 / Windows 11]
Browser (if applicable): [e.g., Firefox 142.0]
Frequency: The issue occurs every time the resume is uploaded.
Attempts to Resolve: Tried refreshing the page and re-uploading; issue persists.
Originally created by @scalenow on GitHub (Sep 18, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/17563
### Check Existing Issues
- [x] I have searched for any existing and/or related issues.
- [x] I have searched for any existing and/or related discussions.
- [x] I am using the latest version of Open WebUI.
### Installation Method
Git Clone
### Open WebUI Version
6.30
### Ollama Version (if applicable)
Mistral 7-b
### Operating System
Ubuntu
### Browser (if applicable)
_No response_
### Confirmation
- [x] I have read and followed all instructions in `README.md`.
- [x] I am using the latest version of **both** Open WebUI and Ollama.
- [x] I have included the browser console logs.
- [x] I have included the Docker container logs.
- [x] I have **provided every relevant configuration, setting, and environment variable used in my setup.**
- [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
- [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps:
- Start with the initial platform/version/OS and dependencies used,
- Specify exact install/launch/configure commands,
- List URLs visited, user input (incl. example values/emails/passwords if needed),
- Describe all options and toggles enabled or changed,
- Include any files or environmental changes,
- Identify the expected and actual result at each stage,
- Ensure any reasonably skilled user can follow and hit the same issue.
### Expected Behavior
Expected Behavior:
When I upload or input my resume into OpenWebUI, the system should correctly read and parse all the content, accurately identifying sections such as work experience, education, and skills, without misplacing or omitting any information.
Description:
When uploading a resume PDF into OpenWebUI, the document analysis summary returned incorrect details that do not exist in the file. For example, the system output mentioned roles at ABC Corporation and XYZ Company, and degrees from University of Michigan and Stanford University, which were not part of the uploaded resume.
This indicates that the document parsing or summarisation function is either hallucinating content or not reading the PDF correctly.
### Actual Behavior
Expected Behavior:
When I upload or input my resume into OpenWebUI, the system should correctly read and parse all the content, accurately identifying sections such as work experience, education, and skills, without misplacing or omitting any information.
### Steps to Reproduce
Steps to Reproduce:
Open OpenWebUI.
Upload a resume PDF (example attached: Abhi Chaturvedi.pdf).
Run the "summarise the resume" prompt.
Observe that the output contains fabricated details not present in the actual resume.
Expected Result:
The system should accurately summarise the uploaded resume contents without fabricating details.
Actual Result:
The system generated a summary with companies, universities, and job details that were not present in the PDF.
Impact:
Incorrect parsing reduces reliability of OpenWebUI’s document analysis features and can mislead users relying on accurate summaries.
Attachments:
Example screenshot of wrong output
Original PDF used for testing
### Logs & Screenshots
<img width="1043" height="547" alt="Image" src="https://github.com/user-attachments/assets/7b9614bd-30d7-465e-8b04-c903644e9754" />
### Additional Information
Additional Details:
Resume Format: The document uploaded is in [specify format, e.g., PDF, DOCX].
Issue Observed: OpenWebUI incorrectly reads the resume content, misplacing or omitting sections such as work experience, education, or skills.
Steps to Reproduce:
Open OpenWebUI.
Upload or paste the resume document.
Observe the parsed output; sections do not match the original content.
Environment Details:
OpenWebUI version: [specify version if known]
Operating System: [e.g., Ubuntu 22.04 / Windows 11]
Browser (if applicable): [e.g., Firefox 142.0]
Frequency: The issue occurs every time the resume is uploaded.
Attempts to Resolve: Tried refreshing the page and re-uploading; issue persists.
GiteaMirror
added the bug label 2026-05-25 09:15:27 -05:00
I am a management consult this should have been the result .this should be the result Accomplished Program Delivery Leader with over 20 years of experience driving complex enterprise
transformations across sectors including government, energy, telecommunications, higher education,
pharmaceuticals, and financial services. Proven success delivering high-value programs in ERP (SAP, Oracle
Fusion), Salesforce CRM, and AI-driven platforms, often in highly regulated, multi-stakeholder environments.
Recognised for leading full-cycle delivery of programs up to $40M AUD, managing cross-functional teams of 60+,
and aligning strategic initiatives with operational execution. Brings deep expertise in Salesforce ecosystem
delivery (Sales, Service, Experience Cloud, CPQ, Marketing Cloud), ERP integrations, and post-M&A system
consolidation.
Combines technical leadership with strong financial acumen, vendor governance, and risk control. Expert in PMI,
SAFe 5.0, Scrum, and hybrid methodologies, with certifications in PMP, TOGAF, AWS, and multiple Agile
frameworks. Adept at stakeholder engagement, business case development, and delivering measurable
outcomes including improved CSAT, cost reductions, and operational efficiency gains.
Strategic advisor and transformation coach, frequently engaged to stabilise at-risk programs, lead enterprise
architecture initiatives, and enable scalable technology foundations for future growth.
<!-- gh-comment-id:3307036976 -->
@scalenow commented on GitHub (Sep 18, 2025):
I am a management consult this should have been the result .this should be the result Accomplished Program Delivery Leader with over 20 years of experience driving complex enterprise
transformations across sectors including government, energy, telecommunications, higher education,
pharmaceuticals, and financial services. Proven success delivering high-value programs in ERP (SAP, Oracle
Fusion), Salesforce CRM, and AI-driven platforms, often in highly regulated, multi-stakeholder environments.
Recognised for leading full-cycle delivery of programs up to $40M AUD, managing cross-functional teams of 60+,
and aligning strategic initiatives with operational execution. Brings deep expertise in Salesforce ecosystem
delivery (Sales, Service, Experience Cloud, CPQ, Marketing Cloud), ERP integrations, and post-M&A system
consolidation.
Combines technical leadership with strong financial acumen, vendor governance, and risk control. Expert in PMI,
SAFe 5.0, Scrum, and hybrid methodologies, with certifications in PMP, TOGAF, AWS, and multiple Agile
frameworks. Adept at stakeholder engagement, business case development, and delivering measurable
outcomes including improved CSAT, cost reductions, and operational efficiency gains.
Strategic advisor and transformation coach, frequently engaged to stabilise at-risk programs, lead enterprise
architecture initiatives, and enable scalable technology foundations for future growth.
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.
Originally created by @scalenow on GitHub (Sep 18, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/17563
Check Existing Issues
Installation Method
Git Clone
Open WebUI Version
6.30
Ollama Version (if applicable)
Mistral 7-b
Operating System
Ubuntu
Browser (if applicable)
No response
Confirmation
README.md.Expected Behavior
Expected Behavior:
When I upload or input my resume into OpenWebUI, the system should correctly read and parse all the content, accurately identifying sections such as work experience, education, and skills, without misplacing or omitting any information.
Description:
When uploading a resume PDF into OpenWebUI, the document analysis summary returned incorrect details that do not exist in the file. For example, the system output mentioned roles at ABC Corporation and XYZ Company, and degrees from University of Michigan and Stanford University, which were not part of the uploaded resume.
This indicates that the document parsing or summarisation function is either hallucinating content or not reading the PDF correctly.
Actual Behavior
Expected Behavior:
When I upload or input my resume into OpenWebUI, the system should correctly read and parse all the content, accurately identifying sections such as work experience, education, and skills, without misplacing or omitting any information.
Steps to Reproduce
Steps to Reproduce:
Open OpenWebUI.
Upload a resume PDF (example attached: Abhi Chaturvedi.pdf).
Run the "summarise the resume" prompt.
Observe that the output contains fabricated details not present in the actual resume.
Expected Result:
The system should accurately summarise the uploaded resume contents without fabricating details.
Actual Result:
The system generated a summary with companies, universities, and job details that were not present in the PDF.
Impact:
Incorrect parsing reduces reliability of OpenWebUI’s document analysis features and can mislead users relying on accurate summaries.
Attachments:
Example screenshot of wrong output
Original PDF used for testing
Logs & Screenshots
Additional Information
Additional Details:
Resume Format: The document uploaded is in [specify format, e.g., PDF, DOCX].
Issue Observed: OpenWebUI incorrectly reads the resume content, misplacing or omitting sections such as work experience, education, or skills.
Steps to Reproduce:
Open OpenWebUI.
Upload or paste the resume document.
Observe the parsed output; sections do not match the original content.
Environment Details:
OpenWebUI version: [specify version if known]
Operating System: [e.g., Ubuntu 22.04 / Windows 11]
Browser (if applicable): [e.g., Firefox 142.0]
Frequency: The issue occurs every time the resume is uploaded.
Attempts to Resolve: Tried refreshing the page and re-uploading; issue persists.
@scalenow commented on GitHub (Sep 18, 2025):
I am a management consult this should have been the result .this should be the result Accomplished Program Delivery Leader with over 20 years of experience driving complex enterprise
transformations across sectors including government, energy, telecommunications, higher education,
pharmaceuticals, and financial services. Proven success delivering high-value programs in ERP (SAP, Oracle
Fusion), Salesforce CRM, and AI-driven platforms, often in highly regulated, multi-stakeholder environments.
Recognised for leading full-cycle delivery of programs up to $40M AUD, managing cross-functional teams of 60+,
and aligning strategic initiatives with operational execution. Brings deep expertise in Salesforce ecosystem
delivery (Sales, Service, Experience Cloud, CPQ, Marketing Cloud), ERP integrations, and post-M&A system
consolidation.
Combines technical leadership with strong financial acumen, vendor governance, and risk control. Expert in PMI,
SAFe 5.0, Scrum, and hybrid methodologies, with certifications in PMP, TOGAF, AWS, and multiple Agile
frameworks. Adept at stakeholder engagement, business case development, and delivering measurable
outcomes including improved CSAT, cost reductions, and operational efficiency gains.
Strategic advisor and transformation coach, frequently engaged to stabilise at-risk programs, lead enterprise
architecture initiatives, and enable scalable technology foundations for future growth.