Open huzaifa0505 opened 1 month ago
Interesting, thanks for the issue! We'll have a look
same here: Query failed: 'NoneType' object is not iterable
OS Ubuntu 24.04
Verba installed via pip add. OLLAMA llama3:70b Python 3.12.3
also the Overview is hanging and not showing any details
Same here as well. Exact same issue. Confirmed Ollama server is working correctly and can interact with the model via the terminal. I get that error on Verba both with Ollama AND with my openAI key ... no logs or error can be seen from the verba server beyond that one
Same Issue here with win11, docker My logs:
(myenv) E:...\Verba>docker compose up time="2024-06-18T15:20:43+03:30" level=warning msg="The \"COHERE_API_KEY\" variable is not set. Defaulting to a blank string." time="2024-06-18T15:20:43+03:30" level=warning msg="The \"OLLAMA_MODEL\" variable is not set. Defaulting to a blank string." time="2024-06-18T15:20:43+03:30" level=warning msg="The \"OLLAMA_EMBED_MODEL\" variable is not set. Defaulting to a blank string." time="2024-06-18T15:20:43+03:30" level=warning msg="The \"UNSTRUCTURED_API_KEY\" variable is not set. Defaulting to a blank string." time="2024-06-18T15:20:43+03:30" level=warning msg="The \"UNSTRUCTURED_API_URL\" variable is not set. Defaulting to a blank string." time="2024-06-18T15:20:43+03:30" level=warning msg="The \"GITHUB_TOKEN\" variable is not set. Defaulting to a blank string." time="2024-06-18T15:20:43+03:30" level=warning msg="The \"COHERE_API_KEY\" variable is not set. Defaulting to a blank string." [+] Running 3/3 ✔ Network verba_default Created 0.0s ✔ Container verba-weaviate-1 Created 0.1s ✔ Container verba-verba-1 Created 0.1s Attaching to verba-1, weaviate-1 weaviate-1 | {"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":"2024-06-18T11:50:43Z"} weaviate-1 | {"action":"startup","auto_schema_enabled":true,"level":"info","msg":"auto schema enabled setting is set to \"true\"","time":"2024-06-18T11:50:43Z"} weaviate-1 | {"level":"info","msg":"No resource limits set, weaviate will use all available memory and CPU. To limit resources, set LIMIT_RESOURCES=true","time":"2024-06-18T11:50:43Z"} weaviate-1 | {"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":"2024-06-18T11:50:43Z"} weaviate-1 | {"action":"grpc_startup","level":"info","msg":"grpc server listening at [::]:50051","time":"2024-06-18T11:50:43Z"} weaviate-1 | {"action":"restapi_management","level":"info","msg":"Serving weaviate at http://[::]:8080","time":"2024-06-18T11:50:43Z"} weaviate-1 | {"level":"info","msg":"Completed loading shard verba_cache_text2vec_cohere_h8d6d8kdLnN0 in 2.015701ms","time":"2024-06-18T11:50:44Z"} weaviate-1 | {"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"main","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-06-18T11:50:44Z","took":64600} weaviate-1 | {"level":"info","msg":"Completed loading shard verba_cache_minilm_azcCKeziv3AZ in 44.680905ms","time":"2024-06-18T11:50:44Z"} weaviate-1 | {"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"main","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-06-18T11:50:44Z","took":88900} weaviate-1 | {"level":"info","msg":"Completed loading shard verba_chunk_text2vec_openai_d6tvOmo1UU7j in 45.285605ms","time":"2024-06-18T11:50:44Z"} weaviate-1 | {"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"main","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-06-18T11:50:44Z","took":94600} weaviate-1 | {"level":"info","msg":"Completed loading shard verba_chunk_minilm_o0bXDw2xfFvO in 45.779305ms","time":"2024-06-18T11:50:44Z"} weaviate-1 | {"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"main","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-06-18T11:50:44Z","took":119400} weaviate-1 | {"level":"info","msg":"Completed loading shard verba_suggestion_b9WiazF0jXQ1 in 88.792909ms","time":"2024-06-18T11:50:45Z"} weaviate-1 | {"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"main","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-06-18T11:50:45Z","took":122100} weaviate-1 | {"level":"info","msg":"Completed loading shard verba_document_text2vec_cohere_jGfFpdka86iH in 89.65201ms","time":"2024-06-18T11:50:45Z"} weaviate-1 | {"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"main","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-06-18T11:50:45Z","took":74600} weaviate-1 | {"level":"info","msg":"Completed loading shard verba_cache_text2vec_openai_sDDxZTWDVcLQ in 94.575411ms","time":"2024-06-18T11:50:45Z"} weaviate-1 | {"level":"info","msg":"Completed loading shard verba_chunk_text2vec_cohere_nKlxG7SKm2FD in 94.766511ms","time":"2024-06-18T11:50:45Z"} weaviate-1 | {"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"main","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-06-18T11:50:45Z","took":84700} weaviate-1 | {"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"main","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-06-18T11:50:45Z","took":131900} weaviate-1 | {"level":"info","msg":"Completed loading shard verba_document_minilm_jwMxtXxMrvU9 in 90.67361ms","time":"2024-06-18T11:50:45Z"} weaviate-1 | {"level":"info","msg":"Completed loading shard verba_document_text2vec_openai_HtZ6JjVPUVsm in 93.73201ms","time":"2024-06-18T11:50:45Z"} weaviate-1 | {"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"main","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-06-18T11:50:45Z","took":105900} weaviate-1 | {"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"main","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-06-18T11:50:45Z","took":145300} weaviate-1 | {"level":"info","msg":"Completed loading shard verba_chunk_ollama_459gPvD5FP6V in 95.952111ms","time":"2024-06-18T11:50:45Z"} weaviate-1 | {"level":"info","msg":"Completed loading shard verba_cache_ollama_gUuJyL8Nqnqu in 95.604711ms","time":"2024-06-18T11:50:45Z"} weaviate-1 | {"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"main","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-06-18T11:50:45Z","took":92900} weaviate-1 | {"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"main","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-06-18T11:50:45Z","took":120100} weaviate-1 | {"level":"info","msg":"Completed loading shard verba_document_ollama_lx0WljQD6OuN in 95.456611ms","time":"2024-06-18T11:50:45Z"} weaviate-1 | {"level":"info","msg":"Completed loading shard verba_config_4IHgCecPRCU1 in 90.97811ms","time":"2024-06-18T11:50:45Z"} weaviate-1 | {"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"main","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-06-18T11:50:45Z","took":99700} weaviate-1 | {"action":"hnsw_vector_cache_prefill","count":3000,"index_id":"main","level":"info","limit":1000000000000,"msg":"prefilled vector cache","time":"2024-06-18T11:50:45Z","took":100800} weaviate-1 | {"action":"telemetry_push","level":"info","msg":"telemetry started","payload":"\u0026{MachineID:4c5d6804-58fd-400a-aa85-103e5b7b31c0 Type:INIT Version:1.24.2 Modules:generative-openai,qna-openai,text2vec-cohere,text2vec-openai NumObjects:0 OS:linux Arch:amd64}","time":"2024-06-18T11:50:45Z"} verba-1 | INFO: Will watch for changes in these directories: ['/Verba'] verba-1 | INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit) verba-1 | INFO: Started reloader process [1] using WatchFiles verba-1 | INFO: Started server process [8] verba-1 | INFO: Waiting for application startup. verba-1 | INFO: Application startup complete. verba-1 | ℹ Setting up client verba-1 | ℹ No Auth information provided verba-1 | ✔ Connected to Weaviate verba-1 | ℹ Setting up components verba-1 | ℹ Retrieve Config From Weaviate verba-1 | ✔ Config Saved in Weaviate verba-1 | ℹ Setting READER to BasicReader verba-1 | ℹ Setting CHUNKER to TokenChunker verba-1 | ℹ Setting EMBEDDER to OllamaEmbedder verba-1 | ℹ Setting RETRIEVER to WindowRetriever verba-1 | ℹ Setting GENERATOR to GPT3 verba-1 | INFO: 127.0.0.1:47102 - "HEAD / HTTP/1.1" 200 OK verba-1 | INFO: 127.0.0.1:52984 - "HEAD / HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:52988 - "GET / HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:52988 - "GET /static/media/2b3f1035ed87a788-s.p.woff2 HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:53018 - "GET /static/media/4049f3f580e14086-s.p.woff2 HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:53004 - "GET /static/media/3d9ea938b6afa941-s.p.woff2 HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:53028 - "GET /static/css/172a34703121a5c4.css HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:53044 - "GET /static/css/7af5f0c0467cb98b.css HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:53052 - "GET /static/media/c9a5bc6a7c948fb0-s.p.woff2 HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:53028 - "GET /static/chunks/webpack-f7ec7a24106fdb21.js HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:53044 - "GET /static/chunks/fd9d1056-13318e87e7edaf08.js HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:53018 - "GET /static/chunks/main-app-6d8fe3bc29305481.js HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:53004 - "GET /static/chunks/bc9c3264-d07564fa5e9c78e4.js HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:53052 - "GET /static/chunks/23-5e3f67a9ac794630.js HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:52988 - "GET /static/chunks/737dfa3e-71fd4aa07f7d84a6.js HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:53028 - "GET /static/chunks/ec3863c0-51ee858d5ca1a7f6.js HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:53052 - "GET /static/chunks/12038df7-6e0eda258325d644.js HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:53044 - "GET /static/chunks/39aecf79-4a889f14de9b85cb.js HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:53018 - "GET /static/chunks/9081a741-61a1020146c5d975.js HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:53028 - "GET /static/chunks/93854f56-29cce777bbb44957.js HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:52988 - "GET /static/chunks/3627521c-57ae5a9df6c7e5b9.js HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:53052 - "GET /static/chunks/558-ac85fa7667d15ac6.js HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:53044 - "GET /static/chunks/app/page-16df460a1ae52a69.js HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:53052 - "GET /api/health HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:53044 - "GET /icon.ico HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:53044 - "GET /api/health HTTP/1.1" 200 OK verba-1 | ℹ Config Retrieved verba-1 | INFO: 172.23.0.1:53044 - "GET /api/config HTTP/1.1" 200 OK verba-1 | INFO: ('172.23.0.1', 53062) - "WebSocket /ws/generate_stream" [accepted] verba-1 | INFO: connection open verba-1 | ✔ Config Saved in Weaviate verba-1 | ℹ Setting READER to BasicReader verba-1 | ℹ Setting CHUNKER to TokenChunker verba-1 | ℹ Setting EMBEDDER to OllamaEmbedder verba-1 | ℹ Setting RETRIEVER to WindowRetriever verba-1 | ℹ Setting GENERATOR to GPT3 verba-1 | INFO: 172.23.0.1:53044 - "POST /api/set_config HTTP/1.1" 200 OK verba-1 | INFO: 127.0.0.1:53074 - "HEAD / HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:53044 - "POST /api/suggestions HTTP/1.1" 200 OK verba-1 | INFO: 172.23.0.1:53044 - "POST /api/suggestions HTTP/1.1" 200 OK verba-1 | ✔ Received query: hi verba-1 | ⚠ Query failed: 'NoneType' object is not iterable verba-1 | INFO: 172.23.0.1:53044 - "POST /api/query HTTP/1.1" 200 OK verba-1 | INFO: 127.0.0.1:47890 - "HEAD / HTTP/1.1" 200 OK verba-1 | INFO: 127.0.0.1:47902 - "HEAD / HTTP/1.1" 200 OK
It looks like error is coming from here : https://github.com/weaviate/Verba/blob/412331cbab2f88cc94c8ec531f3a8dca38572808/goldenverba/server/api.py#L286-L302
Seems like manager.retrieve_chunks([payload.query]) is returning None for chunks instead of a list, so it is not iterable on line 301.
My mistake it looks like this error is deeper then that. So it looks like this is happening here: https://github.com/weaviate/Verba/blob/412331cbab2f88cc94c8ec531f3a8dca38572808/goldenverba/components/retriever/WindowRetriever.py#L70 It looks like when Weavite query returns no chunks then query_results["data"]["Get"][chunk_class] is None. I added a check for None here and it correctly propagates back up and then fails up here and says no chunks were returned: https://github.com/weaviate/Verba/blob/412331cbab2f88cc94c8ec531f3a8dca38572808/goldenverba/server/api.py#L307-L315 So that will help make the error more clear that if you do not have any chunks then the system will not work, but does not fix the system.
I guess this leads to the question : Why are no chunks being returned?
I figured this out for myself at least. I looks like although I had Ollama install I had not pulled down llama3. I guess the issue here is that there is no error that states that the model you configured in the env variable actually exists.
I get the same error if my user prompt is too big. Reducing the size allows it to work.
i have completed with all the work, connected the verba with OLLAMA embedder and uploaded the documents on verba
but when i am asking the querry from that docs it is facing this issue and not giving the answer of query given
i have pasted the error below, can anyone help on this?
[[-0.5941087 -0.10167141 -0.6369917 ... -0.5234859 -0.14651886 0.56666654]] ⚠ Query failed: 'data' INFO: 127.0.0.1:52288 - "POST /api/query HTTP/1.1" 200 OK![2](https://github.com/weaviate/Verba/assets/147985218/87d675ad-1f2a-434b-bdea-44bd36939c6f)