github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-05-06 19:08:59 -05:00
Code Issues 1.3k Packages Projects Releases 126 Wiki Activity

issue: Inconsistent Document Handling — Sometimes Added to System Prompt, Sometimes to Chat Message #5972

New Issue
Open
opened 2025-11-11 16:41:07 -06:00 by GiteaMirror · 1 comment
GiteaMirror commented 2025-11-11 16:41:07 -06:00
Owner
Copy Link

Originally created by @sebslight on GitHub (Aug 5, 2025).

Check Existing Issues

  • I have searched the existing issues and discussions.
  • I am using the latest version of Open WebUI.

Installation Method

Git Clone

Open WebUI Version

0.6.18

Ollama Version (if applicable)

No response

Operating System

Ubuntu 22.04

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

  • If Bypass Embedding & Retrieval is enabled the files should be included as part of the current message that uploaded the file, not included in the system message with RAG template.
  • This behavior ensures clarity and control when, for example, comparing two documents or referencing specific content in a structured way.

Actual Behavior

  • Sometimes, documents are appended to the system message, making them persistent context for all future turns, which causes confusion with multiple documents or when switching topics.
  • Other times, they are correctly added to the user message and work as expected — but this behavior seems inconsistent and unpredictable.
  • As a user, I don’t know what controls this behavior (document type? model? size? state of the conversation?).

Steps to Reproduce

  • Enable Bypass Embedding & Retrieval
  • Start a new chat.
  • Upload a document using the "Upload Document" button or drag-and-drop.

Logs & Screenshots

Image

Here you can see that the default RAG Template is still being used on the system message.
Image

  • Using entire document option or Focused Retrieval in the chat file settings doesn't change anything either
Image 
2025-08-05 21:51:46.232 | DEBUG    | open_webui.utils.chat:generate_chat_completion:167 -generate_chat_completion: {
   "model":"or.google/gemini-2.5-flash-lite",
   "messages":[
      {
         "role":"user",
         "content":"### Task:\nGenerate 1-3 broad tags categorizing the main themes of the chat history, along with 1-3 more specific subtopic tags.\n\n### Guidelines:\n- Start with high-level domains (e.g. Science, Technology, Philosophy, Arts, Politics, Business, Health, Sports, Entertainment, Education)\n- Consider including relevant subfields/subdomains if they are strongly represented throughout the conversation\n- If content is too short (less than 3 messages) or too diverse, use only [\"General\"]\n- Use the chat\\'s primary language; default to English if multilingual\n- Prioritize accuracy over specificity\n\n### Output:\nJSON format: { \"tags\": [\"tag1\", \"tag2\", \"tag3\"] }\n\n### Chat History:\n<chat_history>\nUSER: what is this about\nASSISTANT: The data appears to be from a learning or exam preparation platform that tracks a user\\'s progress across various finance-related topics—likely in preparation for exams such as the CFA (Chartered Financial Analyst).\n\nEach entry represents a topic (like \"Options Strategies,\" \"Currency Management,\" or \"Asset Allocation\") and includes metrics such as:\n\n- **Mastery score**: Indicates the user’s current understanding of the topic.\n- **Confidence or error level**: Shows how well the user is likely to perform.\n- **Recent activity**: Dates of last practice and number of questions attempted.\n- **Trend over time**: Tracks improvement or regression in understanding.\n\nThe system also references specific sources (like Kaplan, CFAI, MM), possibly indicating where the questions or study material originated.\n\nOverall, this is a progress tracking dashboard for financial education, helping a learner identify strengths and areas needing improvement.\n</chat_history>"
      }
   ]
},
"stream":false,
"metadata":{
   "user_id":"7f4acd9d...",
   "chat_id":"b798d398...",
   "message_id":"fdee9e6d...",
   "session_id":"LGE5...",
   "filter_ids":[
      
   ],
   "tool_ids":"None",
   "tool_servers":[
      
   ],
   "files":[
      {
         "type":"file",
         "file":{
            "id":"2ed0eba9///",
            "user_id":"7f4acd9d.//",
            "hash":"d68e43702c57c9...",
            "filename":"wis_compressed.json",
            "data":{
               "content":"{\"_meta\":{\"v\":\"2.0\",\"date\":\"2025-08-02\",\"mode\":\"last_error\",\"legend\":{\"topic\":[\"reading\",\"wis\",\"mastery\",\"days_err\",\"n_q\",\"last_err\"],\"hist\":[\"session\",\"wis\",\"true_score\",\"?wis_base\"],\"abbrev\":{\"CS\":\"Case Study\",\"FI\":\"Fixed-Income\",\"Mgmt\":\"Management\",\"Por...5,0.5,0.354]]},\"src\":{\"BC Mock 2\":[\"Standards I-VII\",0.02,1,21],\"CFAI\":[\"Options Strat\",0.036,0.923,3],\"Kaplan Mock 1\":[\"Investment Manager Selection\",0.017,1,20],\"Kaplan Mock 2\":[\"Port Perf Evaluation\",0.019,1,17],\"MM\":[\"Swaps, Forwards, and Futures Strat\",0.153,0.833,2]}}"
            },
            "meta":{
               "name":"wis_compressed.json",
               "content_type":"application/json",
               "size":6171,
               "data":{
                  
               }
            },
            "created_at":1754430696,
            "updated_at":1754430696
         },
         "id":"2ed0eba9...",
         "url":"/api/v1/files/2ed0eba9...",
         "name":"wis_compressed.json",
         "status":"uploaded",
         "size":6171,
         "error":"",
         "itemId":"96655477..."
      }
   ],
   "features":{
      "image_generation":false,
      "code_interpreter":false,
      "web_search":false,
      "memory":true
   },
   "variables":{
      "{{USER_NAME}}":"REDACTED",
      "{{USER_LOCATION}}":"Unknown",
      "{{CURRENT_DATETIME}}":"2025-08-05 17:51:42",
      "{{CURRENT_DATE}}":"2025-08-05",
      "{{CURRENT_TIME}}":"17:51:42",
      "{{CURRENT_WEEKDAY}}":"Tuesday",
      "{{CURRENT_TIMEZONE}}":"America/New_York",
      "{{USER_LANGUAGE}}":"en-US"
   },
   "model":{
      "id":"or.openai/chatgpt-4o-latest",
      "canonical_slug":"openai/chatgpt-4o-latest",
      "hugging_face_id":"None",
      "name":"OpenAI: ChatGPT-4o",
      "created":1723593600,
      "description":"OpenAI ChatGPT 4o is continually updated by OpenAI to point to the current version of GPT-4o used by ChatGPT. It therefore differs slightly from the API version of [GPT-4o](/models/openai/gpt-4o) in that it has additional RLHF. It is intended for research and evaluation.\n\nOpenAI notes that this model is not suited for production use-cases as it may be removed or redirected to another model in the future.",
      "context_length":128000,
      "architecture":{
         "modality":"text+image->text",
         "input_modalities":[
            "text",
            "image"
         ],
         "output_modalities":[
            "text"
         ],
         "tokenizer":"GPT",
         "instruct_type":"None"
      },
      "pricing":{
         "prompt":"0.000005",
         "completion":"0.000015",
         "request":"0",
         "image":"0.007225",
         "audio":"0",
         "web_search":"0",
         "internal_reasoning":"0"
      },
      "top_provider":{
         "context_length":128000,
         "max_completion_tokens":16384,
         "is_moderated":true
      },
      "per_request_limits":"None",
      "supported_parameters":[
         "frequency_penalty",
         "logit_bias",
         "logprobs",
         "max_tokens",
         "presence_penalty",
         "response_format",
         "seed",
         "stop",
         "structured_outputs",
         "temperature",
         "top_logprobs",
         "top_p"
      ],
      "connection_type":"external",
      "owned_by":"openai",
      "openai":{
         "id":"or.openai/chatgpt-4o-latest",
         "canonical_slug":"openai/chatgpt-4o-latest",
         "hugging_face_id":"None",
         "name":"OpenAI: ChatGPT-4o",
         "created":1723593600,
         "description":"OpenAI ChatGPT 4o is continually updated by OpenAI to point to the current version of GPT-4o used by ChatGPT. It therefore differs slightly from the API version of [GPT-4o](/models/openai/gpt-4o) in that it has additional RLHF. It is intended for research and evaluation.\n\nOpenAI notes that this model is not suited for production use-cases as it may be removed or redirected to another model in the future.",
         "context_length":128000,
         "architecture":{
            "modality":"text+image->text",
            "input_modalities":[
               "text",
               "image"
            ],
            "output_modalities":[
               "text"
            ],
            "tokenizer":"GPT",
            "instruct_type":"None"
         },
         "pricing":{
            "prompt":"0.000005",
            "completion":"0.000015",
            "request":"0",
            "image":"0.007225",
            "audio":"0",
            "web_search":"0",
            "internal_reasoning":"0"
         },
         "top_provider":{
            "context_length":128000,
            "max_completion_tokens":16384,
            "is_moderated":true
         },
         "per_request_limits":"None",
         "supported_parameters":[
            "frequency_penalty",
            "logit_bias",
            "logprobs",
            "max_tokens",
            "presence_penalty",
            "response_format",
            "seed",
            "stop",
            "structured_outputs",
            "temperature",
            "top_logprobs",
            "top_p"
         ],
         "connection_type":"external"
      },
      "urlIdx":0,
      "actions":[
         
      ],
      "filters":[
         
      ],
      "tags":[
         
      ]
   },
   "direct":false,
   "function_calling":"native",
   "task":"tags_generation",
   "task_body":{
      "model":"or.openai/chatgpt-4o-latest",
      "messages":[
         {
            "id":"9a8a0fa6...",
            "parentId":"None",
            "childrenIds":[
               "fdee9e6d..."
            ],
            "role":"user",
            "content":"what is this about",
            "files":[
               {
                  "type":"file",
                  "file":{
                     "id":"2ed0eba9...",
                     "user_id":"7f4acd9d...",
                     "hash":"d68e43...",
                     "filename":"wis_compressed.json",
                     "data":{
                        "content":"{\"_meta\":{\"v\":\"2.0\",\"date\":\"2025-08-02\",\"mode\":\"last_error\",\"legend\":{\"topic\":[\"reading\",\"wis\",\"mastery\",\"days_err\",\"n_q\",\"last_err\"],\"hist\":[\"session\",\"wis\",\"true_score\",\"?wis_base\"],\"abbrev\":{\"CS\":\"Case Study\",\"FI\":\"Fixed-Income\",\"Mgmt\":\"Management\",\"Port\":\"Portfolio\",\"Inst\":\"Institutional\",\"Act\":\"Active\",\"Perf\":\"Performance\",\"Strat\":\"Strategies\"}}},\"cfg\":{\"hl\":2.0,\"df\":0.35,\"el\":0.5,\"pa\":2.0,\"pb\":2.0,\"h...src\":{\"BC Mock 2\":[\"Standards I-VII\",0.02,1,21],\"CFAI\":[\"Options Strat\",0.036,0.923,3],\"Kaplan Mock 1\":[\"Investment Manager Selection\",0.017,1,20],\"Kaplan Mock 2\":[\"Port Perf Evaluation\",0.019,1,17],\"MM\":[\"Swaps, Forwards, and Futures Strat\",0.153,0.833,2]}}"
                     },
                     "meta":{
                        "name":"wis_compressed.json",
                        "content_type":"application/json",
                        "size":6171,
                        "data":{
                           
                        }
                     },
                     "created_at":1754430696,
                     "updated_at":1754430696
                  },
                  "id":"2ed0eba9...",
                  "url":"/api/v1/files/2ed0eba9",
                  "name":"wis_compressed.json",
                  "status":"uploaded",
                  "size":6171,
                  "error":"",
                  "itemId":"96655477..."
               }
            ],
            "timestamp":1754430701,
            "models":[
               "or.openai/chatgpt-4o-latest"
            ]
         },
         {
            "parentId":"9a8a0fa6...",
            "id":"fdee9e6d...",
            "childrenIds":[
               
            ],
            "role":"assistant",
            "content":"The data appears to be from a learning or exam preparation platform that tracks a user\\'s progress across various finance-related topics—likely in preparation for exams such as the CFA (Chartered Financial Analyst).\n\nEach entry represents a topic (like \"Options Strategies,\" \"Currency Management,\" or \"Asset Allocation\") and includes metrics such as:\n\n- **Mastery score**: Indicates the user’s current understanding of the topic.\n- **Confidence or error level**: Shows how well the user is likely to perform.\n- **Recent activity**: Dates of last practice and number of questions attempted.\n- **Trend over time**: Tracks improvement or regression in understanding.\n\nThe system also references specific sources (like Kaplan, CFAI, MM), possibly indicating where the questions or study material originated.\n\nOverall, this is a progress tracking dashboard for financial education, helping a learner identify strengths and areas needing improvement.",
            "model":"or.openai/chatgpt-4o-latest",
            "modelName":"OpenAI: ChatGPT-4o",
            "modelIdx":0,
            "timestamp":1754430701,
            "sources":[
               {
                  "source":{
                     "type":"file",
                     "file":{
                        "id":"2ed0eba9...",
                        "user_id":"7f4acd9d...",
                        "hash":"d68e43702c57c...",
                        "filename":"wis_compressed.json",
                        "data":{
                           "content":"{\"_meta\":{\"v\":\"2.0\",\"date\":\"2025-08-02\",\"mode\":\"last_error\",\"legend\":{\"topic\":[\"reading\",\"wis\",\"mastery\",\"days_err\",\"n_q\",\"last_err\"],\"hist\":[\"session\",\"wis\",\"true_score\",\"?wis_base\"],\"abbrev\":{\"CS\":\"Case Study\",\"FI\":\"Fixed-Income\",\"Mgmt\":\"Management\",\"Port\":\"Portfolio\",\"Inst\":\"Institutional\",\"Act\":\"Active\",\"Perf\":\"Performance\",\"Strat\":\"Strategies\"}}},\"cfg\":{\"hl\":2.0,\"df\":0.35,\"el\":0.5,\"pa\":2.0,\"pb\":2.0,\"hlf\":[1.5,[\"2025-08-10\",\"2025-08-15\"]]},\"topics\":[[\"Currency Mgmt: An Intro\",0.769,0.397,0,44,\"2025-08-02\",-1],[\"Case Study in Port Mgmt: Inst\",0.758,0.167,3,8,\"2025-07-30\",1],[\"....75],[7,0.118,0.75]],\"Case Study in Port Mgmt: Inst (SWF)\":[[6,0.354,0.5],[7,0.275,0.5,0.354]]},\"src\":{\"BC Mock 2\":[\"Standards I-VII\",0.02,1,21],\"CFAI\":[\"Options Strat\",0.036,0.923,3],\"Kaplan Mock 1\":[\"Investment Manager Selection\",0.017,1,20],\"Kaplan Mock 2\":[\"Port Perf Evaluation\",0.019,1,17],\"MM\":[\"Swaps, Forwards, and Futures Strat\",0.153,0.833,2]}}"
                        },
                        "meta":{
                           "name":"wis_compressed.json",
                           "content_type":"application/json",
                           "size":6171,
                           "data":{
                              
                           }
                        },
                        "created_at":1754430696,
                        "updated_at":1754430696
                     },
                     "id":"2ed0eba9...",
                     "url":"/api/v1/files/2ed0eba9...",
                     "name":"wis_compressed.json",
                     "status":"uploaded",
                     "size":6171,
                     "error":"",
                     "itemId":"96655477..."
                  },
                  "document":[
                     "{\"_meta\":{\"v\":\"2.0\",\"date\":\"2025-08-02\",\"mode\":\"last_error\",\"legend\":{\"topic\":[\"reading\",\"wis\",\"mastery\",\"days_err\",\"n_q\",\"last_err\"],\"hist\":[\"session\",\"wis\",\"true_score\",\"?wis_base\"],\"abbrev\":{\"CS\":\"Case Study\",\"FI\":\"Fixed-Income\",\"Mgmt\":\"Management\",\"Port\":\"Portfolio\",\"Inst\":\"Institutional\",\"Act\":\"Active\",\"Perf\":\"Performance\",\"Strat\":\"Strategies\"}}},\"cfg\":{\"hl\":2.0,\"df\":0.35,\"el\":0.5,\"pa\":2.0,\"pb\":2.0,\"hlf\":[1.5,...,1,0.083],[7,0.032,1,0.083]],\"Overview of Asset Allocation\":[[3,0.044,1],[4,0.045,1],[5,0.045,1],[6,0.152,0.75],[7,0.118,0.75]],\"Case Study in Port Mgmt: Inst (SWF)\":[[6,0.354,0.5],[7,0.275,0.5,0.354]]},\"src\":{\"BC Mock 2\":[\"Standards I-VII\",0.02,1,21],\"CFAI\":[\"Options Strat\",0.036,0.923,3],\"Kaplan Mock 1\":[\"Investment Manager Selection\",0.017,1,20],\"Kaplan Mock 2\":[\"Port Perf Evaluation\",0.019,1,17],\"MM\":[\"Swaps, Forwards, and Futures Strat\",0.153,0.833,2]}}"
                  ],
                  "metadata":[
                     {
                        "file_id":"2ed0eba9...",
                        "name":"wis_compressed.json"
                     }
                  ]
               }
            ]
         }
      ],
      "chat_id":"b798d398..."
   }
}
}"-"{
   
}

Additional Information

  • Bypass Embedding & Retrieval is enabled
  • Not using local LLMs — using cloud-based models
  • File upload is enabled in all models
Originally created by @sebslight on GitHub (Aug 5, 2025). ### Check Existing Issues - [x] I have searched the existing issues and discussions. - [x] I am using the latest version of Open WebUI. ### Installation Method Git Clone ### Open WebUI Version 0.6.18 ### Ollama Version (if applicable) _No response_ ### Operating System Ubuntu 22.04 ### 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 - If Bypass Embedding & Retrieval is enabled the files should be included as part of the current message that uploaded the file, not included in the system message with RAG template. - This behavior ensures clarity and control when, for example, comparing two documents or referencing specific content in a structured way. ### Actual Behavior - Sometimes, documents are appended to the system message, making them persistent context for all future turns, which causes confusion with multiple documents or when switching topics. - Other times, they are correctly added to the user message and work as expected — but this behavior seems inconsistent and unpredictable. - As a user, I don’t know what controls this behavior (document type? model? size? state of the conversation?). ### Steps to Reproduce - Enable Bypass Embedding & Retrieval - Start a new chat. - Upload a document using the "Upload Document" button or drag-and-drop. ### Logs & Screenshots <img width="627" height="166" alt="Image" src="https://github.com/user-attachments/assets/b05f2c98-25b4-45b6-af3b-414ef9fb0d24" /> Here you can see that the default RAG Template is still being used on the system message. <img width="923" height="473" alt="Image" src="https://github.com/user-attachments/assets/c0813a8d-974f-41cf-aba0-f903f0dbac7b" /> - Using entire document option or Focused Retrieval in the chat file settings doesn't change anything either <img width="582" height="362" alt="Image" src="https://github.com/user-attachments/assets/3e58bb42-23e6-4ea6-b74d-c3abcc4d635b" /> ``` 2025-08-05 21:51:46.232 | DEBUG | open_webui.utils.chat:generate_chat_completion:167 -generate_chat_completion: { "model":"or.google/gemini-2.5-flash-lite", "messages":[ { "role":"user", "content":"### Task:\nGenerate 1-3 broad tags categorizing the main themes of the chat history, along with 1-3 more specific subtopic tags.\n\n### Guidelines:\n- Start with high-level domains (e.g. Science, Technology, Philosophy, Arts, Politics, Business, Health, Sports, Entertainment, Education)\n- Consider including relevant subfields/subdomains if they are strongly represented throughout the conversation\n- If content is too short (less than 3 messages) or too diverse, use only [\"General\"]\n- Use the chat\\'s primary language; default to English if multilingual\n- Prioritize accuracy over specificity\n\n### Output:\nJSON format: { \"tags\": [\"tag1\", \"tag2\", \"tag3\"] }\n\n### Chat History:\n<chat_history>\nUSER: what is this about\nASSISTANT: The data appears to be from a learning or exam preparation platform that tracks a user\\'s progress across various finance-related topics—likely in preparation for exams such as the CFA (Chartered Financial Analyst).\n\nEach entry represents a topic (like \"Options Strategies,\" \"Currency Management,\" or \"Asset Allocation\") and includes metrics such as:\n\n- **Mastery score**: Indicates the user’s current understanding of the topic.\n- **Confidence or error level**: Shows how well the user is likely to perform.\n- **Recent activity**: Dates of last practice and number of questions attempted.\n- **Trend over time**: Tracks improvement or regression in understanding.\n\nThe system also references specific sources (like Kaplan, CFAI, MM), possibly indicating where the questions or study material originated.\n\nOverall, this is a progress tracking dashboard for financial education, helping a learner identify strengths and areas needing improvement.\n</chat_history>" } ] }, "stream":false, "metadata":{ "user_id":"7f4acd9d...", "chat_id":"b798d398...", "message_id":"fdee9e6d...", "session_id":"LGE5...", "filter_ids":[ ], "tool_ids":"None", "tool_servers":[ ], "files":[ { "type":"file", "file":{ "id":"2ed0eba9///", "user_id":"7f4acd9d.//", "hash":"d68e43702c57c9...", "filename":"wis_compressed.json", "data":{ "content":"{\"_meta\":{\"v\":\"2.0\",\"date\":\"2025-08-02\",\"mode\":\"last_error\",\"legend\":{\"topic\":[\"reading\",\"wis\",\"mastery\",\"days_err\",\"n_q\",\"last_err\"],\"hist\":[\"session\",\"wis\",\"true_score\",\"?wis_base\"],\"abbrev\":{\"CS\":\"Case Study\",\"FI\":\"Fixed-Income\",\"Mgmt\":\"Management\",\"Por...5,0.5,0.354]]},\"src\":{\"BC Mock 2\":[\"Standards I-VII\",0.02,1,21],\"CFAI\":[\"Options Strat\",0.036,0.923,3],\"Kaplan Mock 1\":[\"Investment Manager Selection\",0.017,1,20],\"Kaplan Mock 2\":[\"Port Perf Evaluation\",0.019,1,17],\"MM\":[\"Swaps, Forwards, and Futures Strat\",0.153,0.833,2]}}" }, "meta":{ "name":"wis_compressed.json", "content_type":"application/json", "size":6171, "data":{ } }, "created_at":1754430696, "updated_at":1754430696 }, "id":"2ed0eba9...", "url":"/api/v1/files/2ed0eba9...", "name":"wis_compressed.json", "status":"uploaded", "size":6171, "error":"", "itemId":"96655477..." } ], "features":{ "image_generation":false, "code_interpreter":false, "web_search":false, "memory":true }, "variables":{ "{{USER_NAME}}":"REDACTED", "{{USER_LOCATION}}":"Unknown", "{{CURRENT_DATETIME}}":"2025-08-05 17:51:42", "{{CURRENT_DATE}}":"2025-08-05", "{{CURRENT_TIME}}":"17:51:42", "{{CURRENT_WEEKDAY}}":"Tuesday", "{{CURRENT_TIMEZONE}}":"America/New_York", "{{USER_LANGUAGE}}":"en-US" }, "model":{ "id":"or.openai/chatgpt-4o-latest", "canonical_slug":"openai/chatgpt-4o-latest", "hugging_face_id":"None", "name":"OpenAI: ChatGPT-4o", "created":1723593600, "description":"OpenAI ChatGPT 4o is continually updated by OpenAI to point to the current version of GPT-4o used by ChatGPT. It therefore differs slightly from the API version of [GPT-4o](/models/openai/gpt-4o) in that it has additional RLHF. It is intended for research and evaluation.\n\nOpenAI notes that this model is not suited for production use-cases as it may be removed or redirected to another model in the future.", "context_length":128000, "architecture":{ "modality":"text+image->text", "input_modalities":[ "text", "image" ], "output_modalities":[ "text" ], "tokenizer":"GPT", "instruct_type":"None" }, "pricing":{ "prompt":"0.000005", "completion":"0.000015", "request":"0", "image":"0.007225", "audio":"0", "web_search":"0", "internal_reasoning":"0" }, "top_provider":{ "context_length":128000, "max_completion_tokens":16384, "is_moderated":true }, "per_request_limits":"None", "supported_parameters":[ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_logprobs", "top_p" ], "connection_type":"external", "owned_by":"openai", "openai":{ "id":"or.openai/chatgpt-4o-latest", "canonical_slug":"openai/chatgpt-4o-latest", "hugging_face_id":"None", "name":"OpenAI: ChatGPT-4o", "created":1723593600, "description":"OpenAI ChatGPT 4o is continually updated by OpenAI to point to the current version of GPT-4o used by ChatGPT. It therefore differs slightly from the API version of [GPT-4o](/models/openai/gpt-4o) in that it has additional RLHF. It is intended for research and evaluation.\n\nOpenAI notes that this model is not suited for production use-cases as it may be removed or redirected to another model in the future.", "context_length":128000, "architecture":{ "modality":"text+image->text", "input_modalities":[ "text", "image" ], "output_modalities":[ "text" ], "tokenizer":"GPT", "instruct_type":"None" }, "pricing":{ "prompt":"0.000005", "completion":"0.000015", "request":"0", "image":"0.007225", "audio":"0", "web_search":"0", "internal_reasoning":"0" }, "top_provider":{ "context_length":128000, "max_completion_tokens":16384, "is_moderated":true }, "per_request_limits":"None", "supported_parameters":[ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_logprobs", "top_p" ], "connection_type":"external" }, "urlIdx":0, "actions":[ ], "filters":[ ], "tags":[ ] }, "direct":false, "function_calling":"native", "task":"tags_generation", "task_body":{ "model":"or.openai/chatgpt-4o-latest", "messages":[ { "id":"9a8a0fa6...", "parentId":"None", "childrenIds":[ "fdee9e6d..." ], "role":"user", "content":"what is this about", "files":[ { "type":"file", "file":{ "id":"2ed0eba9...", "user_id":"7f4acd9d...", "hash":"d68e43...", "filename":"wis_compressed.json", "data":{ "content":"{\"_meta\":{\"v\":\"2.0\",\"date\":\"2025-08-02\",\"mode\":\"last_error\",\"legend\":{\"topic\":[\"reading\",\"wis\",\"mastery\",\"days_err\",\"n_q\",\"last_err\"],\"hist\":[\"session\",\"wis\",\"true_score\",\"?wis_base\"],\"abbrev\":{\"CS\":\"Case Study\",\"FI\":\"Fixed-Income\",\"Mgmt\":\"Management\",\"Port\":\"Portfolio\",\"Inst\":\"Institutional\",\"Act\":\"Active\",\"Perf\":\"Performance\",\"Strat\":\"Strategies\"}}},\"cfg\":{\"hl\":2.0,\"df\":0.35,\"el\":0.5,\"pa\":2.0,\"pb\":2.0,\"h...src\":{\"BC Mock 2\":[\"Standards I-VII\",0.02,1,21],\"CFAI\":[\"Options Strat\",0.036,0.923,3],\"Kaplan Mock 1\":[\"Investment Manager Selection\",0.017,1,20],\"Kaplan Mock 2\":[\"Port Perf Evaluation\",0.019,1,17],\"MM\":[\"Swaps, Forwards, and Futures Strat\",0.153,0.833,2]}}" }, "meta":{ "name":"wis_compressed.json", "content_type":"application/json", "size":6171, "data":{ } }, "created_at":1754430696, "updated_at":1754430696 }, "id":"2ed0eba9...", "url":"/api/v1/files/2ed0eba9", "name":"wis_compressed.json", "status":"uploaded", "size":6171, "error":"", "itemId":"96655477..." } ], "timestamp":1754430701, "models":[ "or.openai/chatgpt-4o-latest" ] }, { "parentId":"9a8a0fa6...", "id":"fdee9e6d...", "childrenIds":[ ], "role":"assistant", "content":"The data appears to be from a learning or exam preparation platform that tracks a user\\'s progress across various finance-related topics—likely in preparation for exams such as the CFA (Chartered Financial Analyst).\n\nEach entry represents a topic (like \"Options Strategies,\" \"Currency Management,\" or \"Asset Allocation\") and includes metrics such as:\n\n- **Mastery score**: Indicates the user’s current understanding of the topic.\n- **Confidence or error level**: Shows how well the user is likely to perform.\n- **Recent activity**: Dates of last practice and number of questions attempted.\n- **Trend over time**: Tracks improvement or regression in understanding.\n\nThe system also references specific sources (like Kaplan, CFAI, MM), possibly indicating where the questions or study material originated.\n\nOverall, this is a progress tracking dashboard for financial education, helping a learner identify strengths and areas needing improvement.", "model":"or.openai/chatgpt-4o-latest", "modelName":"OpenAI: ChatGPT-4o", "modelIdx":0, "timestamp":1754430701, "sources":[ { "source":{ "type":"file", "file":{ "id":"2ed0eba9...", "user_id":"7f4acd9d...", "hash":"d68e43702c57c...", "filename":"wis_compressed.json", "data":{ "content":"{\"_meta\":{\"v\":\"2.0\",\"date\":\"2025-08-02\",\"mode\":\"last_error\",\"legend\":{\"topic\":[\"reading\",\"wis\",\"mastery\",\"days_err\",\"n_q\",\"last_err\"],\"hist\":[\"session\",\"wis\",\"true_score\",\"?wis_base\"],\"abbrev\":{\"CS\":\"Case Study\",\"FI\":\"Fixed-Income\",\"Mgmt\":\"Management\",\"Port\":\"Portfolio\",\"Inst\":\"Institutional\",\"Act\":\"Active\",\"Perf\":\"Performance\",\"Strat\":\"Strategies\"}}},\"cfg\":{\"hl\":2.0,\"df\":0.35,\"el\":0.5,\"pa\":2.0,\"pb\":2.0,\"hlf\":[1.5,[\"2025-08-10\",\"2025-08-15\"]]},\"topics\":[[\"Currency Mgmt: An Intro\",0.769,0.397,0,44,\"2025-08-02\",-1],[\"Case Study in Port Mgmt: Inst\",0.758,0.167,3,8,\"2025-07-30\",1],[\"....75],[7,0.118,0.75]],\"Case Study in Port Mgmt: Inst (SWF)\":[[6,0.354,0.5],[7,0.275,0.5,0.354]]},\"src\":{\"BC Mock 2\":[\"Standards I-VII\",0.02,1,21],\"CFAI\":[\"Options Strat\",0.036,0.923,3],\"Kaplan Mock 1\":[\"Investment Manager Selection\",0.017,1,20],\"Kaplan Mock 2\":[\"Port Perf Evaluation\",0.019,1,17],\"MM\":[\"Swaps, Forwards, and Futures Strat\",0.153,0.833,2]}}" }, "meta":{ "name":"wis_compressed.json", "content_type":"application/json", "size":6171, "data":{ } }, "created_at":1754430696, "updated_at":1754430696 }, "id":"2ed0eba9...", "url":"/api/v1/files/2ed0eba9...", "name":"wis_compressed.json", "status":"uploaded", "size":6171, "error":"", "itemId":"96655477..." }, "document":[ "{\"_meta\":{\"v\":\"2.0\",\"date\":\"2025-08-02\",\"mode\":\"last_error\",\"legend\":{\"topic\":[\"reading\",\"wis\",\"mastery\",\"days_err\",\"n_q\",\"last_err\"],\"hist\":[\"session\",\"wis\",\"true_score\",\"?wis_base\"],\"abbrev\":{\"CS\":\"Case Study\",\"FI\":\"Fixed-Income\",\"Mgmt\":\"Management\",\"Port\":\"Portfolio\",\"Inst\":\"Institutional\",\"Act\":\"Active\",\"Perf\":\"Performance\",\"Strat\":\"Strategies\"}}},\"cfg\":{\"hl\":2.0,\"df\":0.35,\"el\":0.5,\"pa\":2.0,\"pb\":2.0,\"hlf\":[1.5,...,1,0.083],[7,0.032,1,0.083]],\"Overview of Asset Allocation\":[[3,0.044,1],[4,0.045,1],[5,0.045,1],[6,0.152,0.75],[7,0.118,0.75]],\"Case Study in Port Mgmt: Inst (SWF)\":[[6,0.354,0.5],[7,0.275,0.5,0.354]]},\"src\":{\"BC Mock 2\":[\"Standards I-VII\",0.02,1,21],\"CFAI\":[\"Options Strat\",0.036,0.923,3],\"Kaplan Mock 1\":[\"Investment Manager Selection\",0.017,1,20],\"Kaplan Mock 2\":[\"Port Perf Evaluation\",0.019,1,17],\"MM\":[\"Swaps, Forwards, and Futures Strat\",0.153,0.833,2]}}" ], "metadata":[ { "file_id":"2ed0eba9...", "name":"wis_compressed.json" } ] } ] } ], "chat_id":"b798d398..." } } }"-"{ } ``` ### Additional Information - Bypass Embedding & Retrieval is enabled - Not using local LLMs — using cloud-based models - File upload is enabled in all models
GiteaMirror added the bug label 2025-11-11 16:41:07 -06:00
GiteaMirror commented 2025-11-11 16:41:08 -06:00
Author
Owner
Copy Link

@tjbck commented on GitHub (Aug 13, 2025):

Related #16403

@tjbck commented on GitHub (Aug 13, 2025): Related #16403
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#5972
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?