Error WebSocket Error: Extra data: line 1 column 5 (char 4)

Support
1

Do someone has this error to test verba ?
I build verba from source

WebSocket Error: Extra data: line 1 column 5 (char 4)
ERROR: Exception in ASGI application
json.decoder.JSONDecodeError: Extra data: line 1 column 5 (char 4)

During handling of the above exception, another exception occurred:
TypeError: Object of type JSONDecodeError is not JSON serializable

1 Like
2

Hey, thanks for the issue!
Were you able to install from source successfully, or did any errors occur while installation?

Can you provide more information about when the error occurs? Is it directly on startup of Verba when accessing the site, or is it appearing when querying Verba? Let me know, happy to help! :partying_face:

3

Hi,
I was able to install from source successfully, while installation i had no error.

The error occurs when i want to querying, i just say “Hi” for test and below there is a message who tell me “Websocket Connection Offline”
while it used to show “Websocket Online” before I made the query.

I don’t know if you need more information but tell me if needed :slight_smile: .

Thanks for replying

4

I’d be glad to help you troubleshoot the “WebSocket Error: Extra data” you’re encountering while testing Verba built from source.

Understanding the Error:

  • WebSocket Error: This indicates an issue with the WebSocket connection, which Verba uses for real-time communication.
  • Extra data: This suggests the server received unexpected characters after a valid JSON message.
  • JSONDecodeError: The server tried to parse the received data as JSON but encountered invalid formatting.
  • TypeError: An attempt was made to serialize (convert) the JSONDecodeError object into JSON, which is not possible.

Potential Causes and Solutions:

  1. Incomplete/Corrupted Data:
  • Double-check your Verba code to ensure messages are sent as complete, well-formed JSON strings.
  • Verify that any intermediate processing steps (e.g., data encoding/decoding) aren’t introducing extra characters.
  • Consider using a debugging tool to inspect the raw data being sent over the WebSocket.
  1. Client-Side Issues:
  • If testing from a client application, make sure it’s sending valid JSON messages and handling potential network errors gracefully.
  • Use a tool like browser developer console to inspect client-side errors.
5

Are you able to ingest documents into Verba?

7

Hi,

I am actually having the same issue. Sorry if this is a simple solution.

below is what I see in the terminal up until the error.

INFO:     Will watch for changes in these directories: ['/media/zain/Seagate 1TB/rag application/verba']
INFO:     Uvicorn running on http://localhost:8000 (Press CTRL+C to quit)
INFO:     Started reloader process [24553] using WatchFiles
ℹ Setting up client
ℹ Using Weaviate Embedded
Started /home/zain/.cache/weaviate-embedded: process ID 24558
{"action":"startup","default_vectorizer_module":"none","level":"info","msg":"the default vectorizer modules is set to \"none\", as a result all new schema classes without an explicit vectorizer setting, will use this vectorizer","time":"2024-05-28T15:47:13-05:00"}
{"action":"startup","auto_schema_enabled":true,"level":"info","msg":"auto schema enabled setting is set to \"true\"","time":"2024-05-28T15:47:13-05:00"}
{"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"verba_cache_minilm_OpOxyh0Yh1zs","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-05-28T15:47:13-05:00","took":19019}
{"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"verba_cache_ollama_TrbZXem6A3hA","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-05-28T15:47:13-05:00","took":17690}
{"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"verba_cache_text2vec_cohere_zoy81ihTCKNg","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-05-28T15:47:13-05:00","took":16050}
{"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"verba_cache_text2vec_openai_hW626EysIZbv","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-05-28T15:47:13-05:00","took":17140}
{"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"verba_chunk_minilm_PTizXIKxeTt4","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-05-28T15:47:13-05:00","took":73039}
{"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"verba_chunk_ollama_D3l7vB6x3M4S","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-05-28T15:47:13-05:00","took":25219}
{"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"verba_chunk_text2vec_cohere_G52kMo5c3Sdp","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-05-28T15:47:13-05:00","took":17409}
{"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"verba_chunk_text2vec_openai_RZLxs2iHSQNe","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-05-28T15:47:13-05:00","took":21040}
{"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"verba_config_7aWR2bffor77","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-05-28T15:47:13-05:00","took":22369}
{"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"verba_document_minilm_oBk2EwWpWBxr","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-05-28T15:47:13-05:00","took":17559}
{"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"verba_document_ollama_B5TfvXJ3e9Yu","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-05-28T15:47:13-05:00","took":32719}
{"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"verba_document_text2vec_cohere_EDJ9loflo0Bi","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-05-28T15:47:13-05:00","took":24100}
{"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"verba_document_text2vec_openai_v8nLrQv8CxPb","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-05-28T15:47:13-05:00","took":16710}
{"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"verba_suggestion_NnsmZ4qnwRAx","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-05-28T15:47:13-05:00","took":17989}
{"level":"warning","msg":"Multiple vector spaces are present, GraphQL Explore and REST API list objects endpoint module include params has been disabled as a result.","time":"2024-05-28T15:47:13-05:00"}
{"action":"grpc_startup","level":"info","msg":"grpc server listening at [::]:50051","time":"2024-05-28T15:47:13-05:00"}
{"action":"restapi_management","level":"info","msg":"Serving weaviate at http://127.0.0.1:6666","time":"2024-05-28T15:47:13-05:00"}
✔ Connected to Weaviate
ℹ Setting up components
ℹ Retrieve Config From Weaviate
✔ Config Saved in Weaviate
ℹ Setting READER to BasicReader
ℹ Setting CHUNKER to TokenChunker
ℹ Setting EMBEDDER to OllamaEmbedder
ℹ Setting RETRIEVER to WindowRetriever
ℹ Setting GENERATOR to Ollama
ℹ Updating BasicReader config (document_type) Research  -> Research
ℹ Updating TokenChunker config (overlap) 50 -> 40
INFO:     Started server process [24555]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     127.0.0.1:49100 - "GET / HTTP/1.1" 200 OK
INFO:     127.0.0.1:49100 - "GET /static/media/2b3f1035ed87a788-s.p.woff2 HTTP/1.1" 304 Not Modified
INFO:     127.0.0.1:49128 - "GET /static/media/3d9ea938b6afa941-s.p.woff2 HTTP/1.1" 304 Not Modified
INFO:     127.0.0.1:49142 - "GET /static/media/c9a5bc6a7c948fb0-s.p.woff2 HTTP/1.1" 304 Not Modified
INFO:     127.0.0.1:49138 - "GET /static/media/4049f3f580e14086-s.p.woff2 HTTP/1.1" 304 Not Modified
INFO:     127.0.0.1:49114 - "GET /static/css/afc8501c2b22bb29.css HTTP/1.1" 304 Not Modified
INFO:     127.0.0.1:49156 - "GET /static/css/7af5f0c0467cb98b.css HTTP/1.1" 304 Not Modified
INFO:     127.0.0.1:49100 - "GET /static/chunks/737dfa3e-71fd4aa07f7d84a6.js HTTP/1.1" 304 Not Modified
INFO:     127.0.0.1:49138 - "GET /static/chunks/23-5e3f67a9ac794630.js HTTP/1.1" 304 Not Modified
INFO:     127.0.0.1:49142 - "GET /static/chunks/main-app-6d8fe3bc29305481.js HTTP/1.1" 304 Not Modified
INFO:     127.0.0.1:49114 - "GET /static/chunks/fd9d1056-13318e87e7edaf08.js HTTP/1.1" 304 Not Modified
INFO:     127.0.0.1:49156 - "GET /static/chunks/webpack-f7ec7a24106fdb21.js HTTP/1.1" 304 Not Modified
INFO:     127.0.0.1:49128 - "GET /static/chunks/bc9c3264-d07564fa5e9c78e4.js HTTP/1.1" 304 Not Modified
INFO:     127.0.0.1:49128 - "GET /static/chunks/ec3863c0-51ee858d5ca1a7f6.js HTTP/1.1" 304 Not Modified
INFO:     127.0.0.1:49114 - "GET /static/chunks/39aecf79-4a889f14de9b85cb.js HTTP/1.1" 304 Not Modified
INFO:     127.0.0.1:49156 - "GET /static/chunks/12038df7-6e0eda258325d644.js HTTP/1.1" 304 Not Modified
INFO:     127.0.0.1:49142 - "GET /static/chunks/93854f56-29cce777bbb44957.js HTTP/1.1" 304 Not Modified
INFO:     127.0.0.1:49100 - "GET /static/chunks/3627521c-57ae5a9df6c7e5b9.js HTTP/1.1" 304 Not Modified
INFO:     127.0.0.1:49138 - "GET /static/chunks/9081a741-61a1020146c5d975.js HTTP/1.1" 304 Not Modified
INFO:     127.0.0.1:49138 - "GET /static/chunks/558-ac85fa7667d15ac6.js HTTP/1.1" 304 Not Modified
INFO:     127.0.0.1:49100 - "GET /static/chunks/app/page-a9dac4e4664785de.js HTTP/1.1" 304 Not Modified
INFO:     127.0.0.1:49100 - "GET /api/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:49138 - "GET /icon.ico HTTP/1.1" 304 Not Modified
INFO:     127.0.0.1:49138 - "GET /api/health HTTP/1.1" 200 OK
ℹ Config Retrieved
INFO:     127.0.0.1:49138 - "GET /api/config HTTP/1.1" 200 OK
INFO:     ('127.0.0.1', 49168) - "WebSocket /ws/generate_stream" [accepted]
✔ Config Saved in Weaviate
ℹ Setting READER to BasicReader
ℹ Setting CHUNKER to TokenChunker
ℹ Setting EMBEDDER to OllamaEmbedder
ℹ Setting RETRIEVER to WindowRetriever
ℹ Setting GENERATOR to Ollama
INFO:     127.0.0.1:49138 - "POST /api/set_config HTTP/1.1" 200 OK
INFO:     connection open
⚠ WebSocket connection closed by client.
INFO:     connection closed
✔ Config Saved in Weaviate
ℹ Setting READER to BasicReader
ℹ Setting CHUNKER to TokenChunker
ℹ Setting EMBEDDER to OllamaEmbedder
ℹ Setting RETRIEVER to WindowRetriever
ℹ Setting GENERATOR to Ollama
ℹ Loading in cureus-0015-00000035077.pdf
✔ Loaded 1 documents in 0.63s
Chunking documents: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 195.01it/s]
✔ Chunking completed with 224 chunks in 0.01s
Vectorizing Chunks:   0%|                                                                                                                                                                                                                                   | 0/224 [00:00<?, ?it/s]
Vectorizing document chunks:   0%|                                                                                                                                                                                                                            | 0/1 [00:00<?, ?it/s]
INFO:     127.0.0.1:53612 - "POST /api/import HTTP/1.1" 200 OK

My .env file has

OLLAMA_URL=http://localhost:11434/
OLLAMA_MODEL=llama3
OLLAMA_EMBED_MODEL=mxbai-embed-large

screencapture-localhost-8000-2024-05-28-15_52_59
screencapture-localhost-8000-2024-05-28-15_52_591920×973 89.3 KB

8

experiencing the same issue as @Zain_Syed