I have searched the existing issues and discussions.
I am using the latest version of Open WebUI.
Installation Method
Docker
Open WebUI Version
v0.6.14
Ollama Version (if applicable)
No response
Operating System
Azure Web App (docker compose)
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
Adding a document to a knowledge collection embeds and uploads to the vector store with multitenancy behaviour
Actual Behavior
UI throws error
400: Unexpected Response: 400 (Bad Request) Raw response content: b'{"status":{"error":"Bad request: Index required but not found for \\"metadata.file_id\\" of one of the following types: [uuid, keyword]. Help: Create an index for this key or use a different filter." ...'
"400: Unexpected Response: 400 (Bad Request) Raw response content: b'{"status":{"error":"Bad request: Index required but not found for \\"metadata.file_id\\" of one of the following types: [uuid, keyword]. Help: Create an index for this key or use a different filter." ...'"
A point is created in a qdrant collection called 'open-webui_files' that looks like the following:
Point a7ce8593-14c4-4ff5-b394-aada926362e3 Payload: text test metadata { "source":"test.txt" "name":"test.txt" "created_by":"c5632f3a-7f0d-42e2-9775-774c09a1de28" "file_id":"296df68c-c924-4623-8e64-9c42778c7546" "start_index":0 "hash":"9f86d081884c7d659a2feaa0c55ad015a3bf4f1b2b0b822cd1…" "embedding_config":"{"engine": "openai", "model": "text-embedding-3-la…" } tenant_id file-296df68c-c924-4623-8e64-9c42778c7546
Originally created by @richardosborne14 on GitHub (Jun 13, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/14960
Originally assigned to: @jackthgu on GitHub.
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
- [x] I am using the latest version of Open WebUI.
### Installation Method
Docker
### Open WebUI Version
v0.6.14
### Ollama Version (if applicable)
_No response_
### Operating System
Azure Web App (docker compose)
### 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
Adding a document to a knowledge collection embeds and uploads to the vector store with multitenancy behaviour
### Actual Behavior
UI throws error
`400: Unexpected Response: 400 (Bad Request) Raw response content: b'{"status":{"error":"Bad request: Index required but not found for \\"metadata.file_id\\" of one of the following types: [uuid, keyword]. Help: Create an index for this key or use a different filter." ...'
`
### Steps to Reproduce
1. Spin up Open WebUI with env variables for Qdrant:
- VECTOR_DB=qdrant
- QDRANT_API_KEY=eyJhb4ciO...
- QDRANT_URI=https://a3917400-f3cd-401-90874-241c5a0a961.uksouth-0.azure.cloud.qdrant.io:6333
- ENABLE_QDRANT_MULTITENANCY_MODE=True
2. Create a new Knowledge collection
3. Add a test text document with dummy text
4. Receive error indicated above
### Logs & Screenshots
Console logs:
`"400: Unexpected Response: 400 (Bad Request)
Raw response content:
b'{"status":{"error":"Bad request: Index required but not found for \\"metadata.file_id\\" of one of the following types: [uuid, keyword]. Help: Create an index for this key or use a different filter." ...'"`
Full docker compose config:
`version: '3'
services:
open-webui-deepinfra:
image: ghcr.io/open-webui/open-webui:0.6.14
container_name: open-webui-deepinfra
ports:
- "8080:8080"
environment:
# Existing environment variables
- ENV=production
- DEFAULT_USER_ROLE=pending
- ENABLE_SIGNUP=True
- OPENAI_API_BASE_URLS=https://api.groq.com/openai/v1
- OPENAI_API_KEYS=gsk_...
- ENABLE_OLLAMA=False
- PORT=8080
- WEBSITES_PORT=8080
- WEBSITES_ENABLE_APP_SERVICE_STORAGE=true
- DOCKER_ENABLE_CI=true
# Database configuration
- DATABASE_URL=postgresql://redacted:redacted@directus.postgres.database.azure.com/postgres
- DATABASE_SCHEMA=public
- DATABASE_POOL_SIZE=10
- DATABASE_POOL_MAX_OVERFLOW=20
- DATABASE_POOL_TIMEOUT=30
- DATABASE_POOL_RECYCLE=3600
- VECTOR_DB=qdrant
- QDRANT_API_KEY=xyz...
- QDRANT_URI=https://a3971300-f8cd-431-9084-2371c5701.uksouth-0.azure.cloud.qdrant.io:6333
- ENABLE_QDRANT_MULTITENANCY_MODE=True
# Azure Storage configuration
- AZURE_STORAGE_ENDPOINT=https://redacted.blob.core.windows.net
- AZURE_STORAGE_CONTAINER_NAME=openwebui
- AZURE_STORAGE_KEY=xyz...
volumes:
- openwebui_data2:/app/backend/data # Persistent storage for OpenWebUI
- openwebui_cache:/root/.cache # Cache directory persistence
volumes:
openwebui_data2:
openwebui_cache:`
### Additional Information
A point is created in a qdrant collection called 'open-webui_files' that looks like the following:
`Point a7ce8593-14c4-4ff5-b394-aada926362e3
Payload:
text
test
metadata
{
"source":"test.txt"
"name":"test.txt"
"created_by":"c5632f3a-7f0d-42e2-9775-774c09a1de28"
"file_id":"296df68c-c924-4623-8e64-9c42778c7546"
"start_index":0
"hash":"9f86d081884c7d659a2feaa0c55ad015a3bf4f1b2b0b822cd1…"
"embedding_config":"{"engine": "openai", "model": "text-embedding-3-la…"
}
tenant_id
file-296df68c-c924-4623-8e64-9c42778c7546`
GiteaMirror
added the bug label 2026-05-13 03:59:36 -05:00
We have confirmed that the Vector DB setup works fine using Qdrant in a Docker environment. Could you please test it in Docker first?
Thank you!
<!-- gh-comment-id:2979046760 -->
@jackthgu commented on GitHub (Jun 17, 2025):
We have confirmed that the Vector DB setup works fine using Qdrant in a Docker environment. Could you please test it in Docker first?
Thank you!
We're unable to reproduce with the description you've provided, could you provide the document you've used as well to rule out the document issue?
<!-- gh-comment-id:2979878680 -->
@tjbck commented on GitHub (Jun 17, 2025):
We're unable to reproduce with the description you've provided, could you provide the document you've used as well to rule out the document issue?
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 @richardosborne14 on GitHub (Jun 13, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/14960
Originally assigned to: @jackthgu on GitHub.
Check Existing Issues
Installation Method
Docker
Open WebUI Version
v0.6.14
Ollama Version (if applicable)
No response
Operating System
Azure Web App (docker compose)
Browser (if applicable)
No response
Confirmation
README.md.Expected Behavior
Adding a document to a knowledge collection embeds and uploads to the vector store with multitenancy behaviour
Actual Behavior
UI throws error
400: Unexpected Response: 400 (Bad Request) Raw response content: b'{"status":{"error":"Bad request: Index required but not found for \\"metadata.file_id\\" of one of the following types: [uuid, keyword]. Help: Create an index for this key or use a different filter." ...'Steps to Reproduce
Logs & Screenshots
Console logs:
"400: Unexpected Response: 400 (Bad Request) Raw response content: b'{"status":{"error":"Bad request: Index required but not found for \\"metadata.file_id\\" of one of the following types: [uuid, keyword]. Help: Create an index for this key or use a different filter." ...'"Full docker compose config:
`version: '3'
services:
open-webui-deepinfra:
image: ghcr.io/open-webui/open-webui:0.6.14
container_name: open-webui-deepinfra
ports:
- "8080:8080"
environment:
# Existing environment variables
- ENV=production
- DEFAULT_USER_ROLE=pending
- ENABLE_SIGNUP=True
- OPENAI_API_BASE_URLS=https://api.groq.com/openai/v1
- OPENAI_API_KEYS=gsk_...
- ENABLE_OLLAMA=False
- PORT=8080
- WEBSITES_PORT=8080
- WEBSITES_ENABLE_APP_SERVICE_STORAGE=true
- DOCKER_ENABLE_CI=true
volumes:
openwebui_data2:
openwebui_cache:`
Additional Information
A point is created in a qdrant collection called 'open-webui_files' that looks like the following:
Point a7ce8593-14c4-4ff5-b394-aada926362e3 Payload: text test metadata { "source":"test.txt" "name":"test.txt" "created_by":"c5632f3a-7f0d-42e2-9775-774c09a1de28" "file_id":"296df68c-c924-4623-8e64-9c42778c7546" "start_index":0 "hash":"9f86d081884c7d659a2feaa0c55ad015a3bf4f1b2b0b822cd1…" "embedding_config":"{"engine": "openai", "model": "text-embedding-3-la…" } tenant_id file-296df68c-c924-4623-8e64-9c42778c7546@jackthgu commented on GitHub (Jun 17, 2025):
We have confirmed that the Vector DB setup works fine using Qdrant in a Docker environment. Could you please test it in Docker first?
Thank you!
@tjbck commented on GitHub (Jun 17, 2025):
We're unable to reproduce with the description you've provided, could you provide the document you've used as well to rule out the document issue?