Verba pdf import fails: Unexpected status code: 500, Connection refused.

Taikan · January 2, 2026, 6:53pm

Description

Hello! Please excuse my clumsiness as I’ve been out of the programming world for some years and am new to the AI domain. Happy to be here

I’m running Weaviate, Verba, and Ollama in a docker container. My pdf imports consistently fail with the following error message found in the debug window of the verba UI.

"ERROR": {
  "fileID": "Happiness - Thich Nhat Hanh.pdf",
  "status": "ERROR",
  "message": "Import for Happiness - Thich Nhat Hanh.pdf failed: Import for Happiness - Thich Nhat Hanh.pdf failed: Object was not added! Unexpected status code: 500, with response body: {'error': [{'message': 'vectorize target vector : update vector: send POST request: Post \"http://localhost:11434/api/embed\": dial tcp [::1]:11434: connect: connection refused'}]}.",
  "took": 0
}

I’ve been assuming that this localhost reference in the error msg is the problem in the communication between containers. I’m setting OLLAMA_URL: ‘http://ollama:11434’ in the docker-compose file and thats being picked up by the ollamaembedder so I’m not sure where thats coming from. Could be totally off base though. Any advice is appreciated!

Below are the logs from verba and ollama. Python version is 3.11.14, Weaviate is 1.30. Ollama is 0.13.5, cant find out how to verify Verba version but just pulled it a couple of days ago.

Server Setup Information

Weaviate Server Version: 1.3
Deployment Method: docker
Multi Node? Number of Running Nodes:
Client Language and Version:
Multitenancy?:

Any additional Information

VERBA LOG

((verbaenv) ) gregoire@Edward weaviate % docker compose up -d
[+] Running 4/4
Network weaviate_default Created 0.0s
Container weaviate Started 0.2s
Container ollama Started 0.2s
Container verba Started 0.3s
((verbaenv) ) gregoire@Edward weaviate % docker logs -f verba
pandas not installed, Excel functionality will be limited.
[DEBUG] OllamaEmbedder OLLAMA_URL = http://ollama:11434
INFO: Will watch for changes in these directories: [‘/Verba’]
WARNING: “workers” flag is ignored when reloading is enabled.
INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
INFO: Started reloader process [1] using WatchFiles
pandas not installed, Excel functionality will be limited.
[DEBUG] OllamaEmbedder OLLAMA_URL = http://ollama:11434
/usr/local/lib/python3.11/site-packages/websockets/legacy/init.py:6: DeprecationWarning: websockets.legacy is deprecated; see Upgrade to the new asyncio implementation - websockets 15.0.1 documentation for upgrade instructions
warnings.warn( # deprecated in 14.0 - 2024-11-09
/usr/local/lib/python3.11/site-packages/uvicorn/protocols/websockets/websockets_impl.py:14: DeprecationWarning: websockets.server.WebSocketServerProtocol is deprecated
from websockets.server import WebSocketServerProtocol
INFO: Started server process [26]
INFO: Waiting for application startup.
INFO: Application startup complete.
INFO: 172.64.66.1:32448 - “GET / HTTP/1.1” 200 OK
INFO: 172.64.66.1:32448 - “GET /static/_next/static/media/4049f3f580e14086-s.p.woff2 HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:16855 - “GET /static/_next/static/media/5d258b355fefebcb-s.p.woff2 HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:43311 - “GET /static/_next/static/css/ae5cf92d392439f8.css HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:25114 - “GET /static/_next/static/media/636a5ac981f94f8b-s.p.woff2 HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:29517 - “GET /static/_next/static/css/fd8d77da4d075ee8.css HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:32448 - “GET /static/_next/static/chunks/webpack-f81a484e456a776b.js HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:29898 - “GET /static/_next/static/media/e4af272ccee01ff0-s.p.woff2 HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:43311 - “GET /static/_next/static/chunks/117-2e3ee50cbb6fc8da.js HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:29517 - “GET /static/_next/static/chunks/b536a0f1-d8ed58bb9dee20ad.js HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:25114 - “GET /static/_next/static/chunks/main-app-8b51a742f61d77e1.js HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:29898 - “GET /static/_next/static/chunks/472688b4-f8d4a7fb6705064c.js HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:16855 - “GET /static/_next/static/chunks/fd9d1056-aa9b9ca480dc9276.js HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:29517 - “GET /static/_next/static/chunks/48507feb-fb2bbcdbd4adc32f.js HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:29898 - “GET /static/_next/static/chunks/bc9c3264-ebee20cfb15b0079.js HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:32448 - “GET /static/_next/static/chunks/5349c568-74bb20b84335457b.js HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:25114 - “GET /static/_next/static/chunks/4f9d9cd8-0af0a6a5e34c4b59.js HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:43311 - “GET /static/_next/static/chunks/ec3863c0-06201a77cd4ecf61.js HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:16855 - “GET /static/_next/static/chunks/12038df7-a10f1b9476e02872.js HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:29517 - “GET /static/_next/static/chunks/39aecf79-2d831b66f40a6478.js HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:29898 - “GET /static/_next/static/chunks/8e68d877-6d32d357377fbcf8.js HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:16855 - “GET /static/_next/static/chunks/07115393-160e96bd79d1e493.js HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:32448 - “GET /static/_next/static/chunks/39209d7c-f601708f0876481f.js HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:29898 - “GET /static/_next/static/chunks/514-cff62b6f7919676e.js HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:25114 - “GET /static/_next/static/chunks/8dc5345f-59beaec077e947c5.js HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:29517 - “GET /static/_next/static/chunks/4f53ad1b-f1821b28dab6f189.js HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:43311 - “GET /static/_next/static/chunks/9081a741-a7c6599b4221aee8.js HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:16855 - “GET /static/_next/static/chunks/app/page-f09784266b0febdd.js HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:16855 - “GET /icon.ico HTTP/1.1” 404 Not Found
Cleaning Clients Cache
Cleaned up 0 clients
0 clients connected
INFO: 172.64.66.1:16855 - “GET /api/health HTTP/1.1” 200 OK
INFO: 172.64.66.1:43311 - “GET /static/icon.ico HTTP/1.1” 304 Not Modified
Cleaning Clients Cache
Cleaned up 0 clients
0 clients connected
INFO: 172.64.66.1:43311 - “GET /api/health HTTP/1.1” 200 OK
INFO: 172.64.66.1:43311 - “GET /static/verba.glb HTTP/1.1” 304 Not Modified
INFO: 172.64.66.1:43311 - “GET /static/ice_cap.png HTTP/1.1” 304 Not Modified
Cleaning Clients Cache
Cleaned up 0 clients
0 clients connected
INFO: 172.64.66.1:33511 - “GET /api/health HTTP/1.1” 200 OK
/usr/local/lib/python3.11/site-packages/weaviate/warnings.py:133: DeprecationWarning: Dep005: You are using weaviate-client version 4.9.6. The latest version is 4.19.2.
Consider upgrading to the latest version. See Python | Weaviate Documentation for details.
warnings.warn(
Connecting new Client
Connecting to Weaviate Docker
Succesfully Connected to Weaviate
Connection time: 0.15 seconds
Using New RAG Configuration
INFO: 172.64.66.1:33511 - “POST /api/connect HTTP/1.1” 200 OK
Cleaning Clients Cache
Cleaned up 0 clients
1 clients connected
Client
74bc4a71669a8426593db2739daf2d42212c0901f2500d54408387ee55dbc2f2 connected at
2026-01-02 13:21:05.806299
INFO: 172.64.66.1:33511 - “GET /api/health HTTP/1.1” 200 OK
/usr/local/lib/python3.11/site-packages/websockets/legacy/server.py:1178: DeprecationWarning: remove second argument of ws_handler
warnings.warn(“remove second argument of ws_handler”, DeprecationWarning)
INFO: (‘172.64.66.1’, 58035) - “WebSocket /ws/generate_stream” [accepted]
INFO: connection open
Cleaning Clients Cache
Cleaned up 0 clients
1 clients connected
Client
74bc4a71669a8426593db2739daf2d42212c0901f2500d54408387ee55dbc2f2 connected at
2026-01-02 13:21:05.806299
INFO: 172.64.66.1:33511 - “GET /api/health HTTP/1.1” 200 OK
Cleaning Clients Cache
Cleaned up 0 clients
1 clients connected
Client
74bc4a71669a8426593db2739daf2d42212c0901f2500d54408387ee55dbc2f2 connected at
2026-01-02 13:21:05.806299
INFO: 172.64.66.1:33511 - “GET /api/health HTTP/1.1” 200 OK
/usr/local/lib/python3.11/site-packages/websockets/exceptions.py:125: DeprecationWarning: ConnectionClosed.code is deprecated; use Protocol.close_code or ConnectionClosed.rcvd.code
warnings.warn( # deprecated in 13.1 - 2024-09-21
INFO: connection closed
WebSocket connection closed by client.
Found existing Client
Found existing Client
INFO: 172.64.66.1:33511 - “POST /api/get_datacount HTTP/1.1” 200 OK
Found existing Client
INFO: 172.64.66.1:27535 - “POST /api/get_datacount HTTP/1.1” 200 OK
INFO: (‘172.64.66.1’, 32369) - “WebSocket /ws/generate_stream” [accepted]
INFO: connection open
Cleaning Clients Cache
Cleaned up 0 clients
1 clients connected
Client
74bc4a71669a8426593db2739daf2d42212c0901f2500d54408387ee55dbc2f2 connected at
2026-01-02 13:21:05.806299
INFO: 172.64.66.1:33511 - “GET /api/health HTTP/1.1” 200 OK
Cleaning Clients Cache
Found existing Client
Cleaned up 0 clients
1 clients connected
Client
74bc4a71669a8426593db2739daf2d42212c0901f2500d54408387ee55dbc2f2 connected at
2026-01-02 13:21:05.806299
INFO: 172.64.66.1:33511 - “GET /api/health HTTP/1.1” 200 OK
Found existing Client
INFO: 172.64.66.1:27535 - “POST /api/get_labels HTTP/1.1” 200 OK
INFO: 172.64.66.1:47853 - “POST /api/get_meta HTTP/1.1” 200 OK
INFO: 172.64.66.1:33511 - “POST /api/get_labels HTTP/1.1” 200 OK
INFO: (‘172.64.66.1’, 39737) - “WebSocket /ws/import_files” [accepted]
INFO: connection open
Cleaning Clients Cache
Cleaned up 0 clients
1 clients connected
Client
74bc4a71669a8426593db2739daf2d42212c0901f2500d54408387ee55dbc2f2 connected at
2026-01-02 13:21:05.806299
INFO: 172.64.66.1:33511 - “GET /api/health HTTP/1.1” 200 OK
Found existing Client
INFO: 172.64.66.1:33511 - “POST /api/get_datacount HTTP/1.1” 200 OK
Cleaning Clients Cache
Cleaned up 0 clients
1 clients connected
Client
74bc4a71669a8426593db2739daf2d42212c0901f2500d54408387ee55dbc2f2 connected at
2026-01-02 13:21:05.806299
INFO: 172.64.66.1:33511 - “GET /api/health HTTP/1.1” 200 OK
Found existing Client
INFO: 172.64.66.1:33511 - “POST /api/get_labels HTTP/1.1” 200 OK

OLLAMA LOG

gregoire@Edward weaviate % docker logs -f ollama
time=2026-01-02T13:20:23.355Z level=INFO source=routes.go:1554 msg=“server config” env=“map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]”
time=2026-01-02T13:20:23.356Z level=INFO source=images.go:493 msg=“total blobs: 6”
time=2026-01-02T13:20:23.356Z level=INFO source=images.go:500 msg=“total unused blobs removed: 0”
time=2026-01-02T13:20:23.356Z level=INFO source=routes.go:1607 msg=“Listening on [::]:11434 (version 0.13.5)”
time=2026-01-02T13:20:23.357Z level=INFO source=runner.go:67 msg=“discovering available GPUs…”
time=2026-01-02T13:20:23.357Z level=INFO source=server.go:429 msg=“starting runner” cmd=“/usr/bin/ollama runner --ollama-engine --port 36643”
time=2026-01-02T13:20:23.375Z level=INFO source=server.go:429 msg=“starting runner” cmd=“/usr/bin/ollama runner --ollama-engine --port 33105”
time=2026-01-02T13:20:23.401Z level=INFO source=types.go:60 msg=“inference compute” id=cpu library=cpu compute=“” name=cpu description=cpu libdirs=ollama driver=“” pci_id=“” type=“” total=“7.7 GiB” available=“7.6 GiB”
time=2026-01-02T13:20:23.401Z level=INFO source=routes.go:1648 msg=“entering low vram mode” “total vram”=“0 B” threshold=“20.0 GiB”
[GIN] 2026/01/02 - 13:20:25 | 200 | 485µs | 172.18.0.4 | GET “/api/tags”
[GIN] 2026/01/02 - 13:20:25 | 200 | 161.042µs | 172.18.0.4 | GET “/api/tags”
[GIN] 2026/01/02 - 13:20:27 | 200 | 800.333µs | 172.18.0.4 | GET “/api/tags”
[GIN] 2026/01/02 - 13:20:27 | 200 | 159.208µs | 172.18.0.4 | GET “/api/tags”
time=2026-01-02T13:21:31.779Z level=WARN source=cpu_linux.go:130 msg=“failed to parse CPU allowed micro secs” error=“strconv.ParseInt: parsing "max": invalid syntax”
time=2026-01-02T13:21:31.787Z level=WARN source=server.go:167 msg=“requested context size too large for model” num_ctx=8192 n_ctx_train=2048
time=2026-01-02T13:21:31.788Z level=INFO source=server.go:429 msg=“starting runner” cmd=“/usr/bin/ollama runner --ollama-engine --model /root/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6 --port 42659”
time=2026-01-02T13:21:31.789Z level=INFO source=sched.go:443 msg=“system memory” total=“7.7 GiB” free=“7.6 GiB” free_swap=“1024.0 MiB”
time=2026-01-02T13:21:31.790Z level=INFO source=server.go:746 msg=“loading model” “model layers”=13 requested=-1
time=2026-01-02T13:21:31.869Z level=INFO source=runner.go:1405 msg=“starting ollama engine”
time=2026-01-02T13:21:31.874Z level=INFO source=runner.go:1440 msg=“Server listening on 127.0.0.1:42659”
time=2026-01-02T13:21:31.884Z level=INFO source=runner.go:1278 msg=load request=“{Operation:fit LoraPath: Parallel:1 BatchSize:512 FlashAttention:Disabled KvSize:2048 KvCacheType: NumThreads:10 GPULayers: MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}”
time=2026-01-02T13:21:31.894Z level=INFO source=ggml.go:136 msg=“” architecture=nomic-bert file_type=F16 name=nomic-embed-text-v1.5 description=“” num_tensors=112 num_key_values=25
load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu.so
time=2026-01-02T13:21:31.897Z level=INFO source=ggml.go:104 msg=system CPU.0.NEON=1 CPU.0.ARM_FMA=1 CPU.0.LLAMAFILE=1 CPU.1.NEON=1 CPU.1.ARM_FMA=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang)
time=2026-01-02T13:21:31.898Z level=WARN source=runner.go:1213 msg=“model does not support caching, setting batch size to context length” batch_size=2048
time=2026-01-02T13:21:31.901Z level=INFO source=runner.go:1278 msg=load request=“{Operation:alloc LoraPath: Parallel:1 BatchSize:512 FlashAttention:Disabled KvSize:2048 KvCacheType: NumThreads:10 GPULayers: MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}”
time=2026-01-02T13:21:31.906Z level=WARN source=runner.go:1213 msg=“model does not support caching, setting batch size to context length” batch_size=2048
time=2026-01-02T13:21:31.907Z level=INFO source=runner.go:1278 msg=load request=“{Operation:commit LoraPath: Parallel:1 BatchSize:512 FlashAttention:Disabled KvSize:2048 KvCacheType: NumThreads:10 GPULayers: MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}”
time=2026-01-02T13:21:31.907Z level=INFO source=device.go:245 msg=“model weights” device=CPU size=“305.6 MiB”
time=2026-01-02T13:21:31.907Z level=INFO source=device.go:267 msg=“compute graph” device=CPU size=“234.0 MiB”
time=2026-01-02T13:21:31.907Z level=INFO source=device.go:272 msg=“total memory” size=“539.6 MiB”
time=2026-01-02T13:21:31.907Z level=INFO source=sched.go:517 msg=“loaded runners” count=1
time=2026-01-02T13:21:31.907Z level=INFO source=ggml.go:482 msg=“offloading 0 repeating layers to GPU”
time=2026-01-02T13:21:31.907Z level=INFO source=ggml.go:486 msg=“offloading output layer to CPU”
time=2026-01-02T13:21:31.907Z level=INFO source=ggml.go:494 msg=“offloaded 0/13 layers to GPU”
time=2026-01-02T13:21:31.907Z level=INFO source=server.go:1338 msg=“waiting for llama runner to start responding”
time=2026-01-02T13:21:31.908Z level=INFO source=server.go:1372 msg=“waiting for server to become available” status=“llm server loading model”
time=2026-01-02T13:21:32.160Z level=INFO source=server.go:1376 msg=“llama runner started in 0.37 seconds”
[GIN] 2026/01/02 - 13:22:35 | 200 | 1m3s | 172.18.0.4 | POST “/api/embed”
[GIN] 2026/01/02 - 13:22:54 | 200 | 1m22s | 172.18.0.4 | POST “/api/embed”

DudaNogueira · January 2, 2026, 6:57pm

Hi @Taikan !! Welcome to our community

Where are you setting OLLAMA_URL ? This should be set on the docker env variable.

The error points to Verba trying to vectorize at http://localhost:11434/api/embed, and not being able to connect.

Notice: We now have an “evolved” Verba called Elysia: https://elysia.weaviate.io/ that has an agentic approach instead of naive RAG, like in Verba.

Also, Verba is not a product, but a project, and is no longer maintained: GitHub - weaviate/Verba: Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

Thanks!

Taikan · January 2, 2026, 8:32pm

Thanks for your reply Duda!

I’m setting it to:
OLLAMA_URL: ‘http://ollama:11434’
in the verba environments section of the docker-compose file. I’ll list the contents of the file below. I’ve verified that it gets stored off properly in self.url in the OllamaEmbedder class.

Any idea why this reference to localhost is popping up? Is it a plausible setup to run ollama in a docker container on the same network as verba and weaviate?

Thanks for the info on Elysia. That looks seriously next level ! The pre-baked UI that Verba provides is pretty attractive in terms of getting something running quick but I’m curious to learn more about Elysia .