Current Status: Endpoint Ignored in text2vec-ollama Module

lssindustry4 · July 19, 2025, 11:27pm

In Query-time text2vec-ollama module ignores custom endpoint and always falls back to localhost:11434

I have Weaviate, pipelines and Open WebUI containers sharing the same custom bridge network

I can run Langchain Python script and generate the embedding.

When I query using Open WebUI and pipelines, it falls back to localhost as explained above

OS is Windows Pro 11
Ollama runs in the host computer
I use Docker Desktop

All the environment variables are set properly

Mohamed_Shahin · July 23, 2025, 12:47pm

Hi @lssindustry4,

Welcome to our community, it’s great to have you with us!

Just to confirm, is this the same issue as reported here?

github.com/weaviate/weaviate

Query-time text2vec-ollama module ignores custom endpoint and always falls back to localhost:11434

opened 09:35AM - 15 Jun 25 UTC

qi20099

**Description** I’m running Weaviate v1.30.8 in Docker Compose and hosting Ollam…a (BGE-M3) on my physical machine at 192.168.1.217:11434. Although embedding via Ollama works from the host, any query-time vectorization in Weaviate still tries to POST to http://localhost:11434/api/embed and fails with connection refused. Neither environment variables nor schema settings seem to take effect. **Environment** Weaviate version: v1.30.8 (Docker image semitechnologies/weaviate:latest) Deployment: Docker Compose (bridge network), ports 8088:8080, 50051:50051 Ollama service: Running on host 192.168.1.217:11434, responds correctly to: bash curl -X POST http://192.168.1.217:11434/api/embed \ -H 'Content-Type: application/json' \ -d '{"model":"bge-m3","input":"test"}' **Client: Java SDK v5.2.1, using** java .targetVectors(new String[]{ "title" }) to trigger query-time embedding **Docker Compose snippet** yaml services: weaviate: image: semitechnologies/weaviate:latest ports: - "8088:8080" - "50051:50051" volumes: - /opt/weaviate/data:/var/lib/weaviate extra_hosts: - "host.docker.internal:host-gateway" environment: PERSISTENCE_DATA_PATH: "/var/lib/weaviate" ENABLE_API_BASED_MODULES: "true" ENABLE_MODULES: "text2vec-ollama,generative-ollama" DEFAULT_VECTORIZER_MODULE: "text2vec-ollama" TEXT2VEC_OLLAMA_API_ENDPOINT: "http://host.docker.internal:11434 CLUSTER_HOSTNAME: "node1" command: - --host - "0.0.0.0" - --port - "8080" - --scheme - "http" - --write-timeout - "600s" **Schema configuration (Java SDK)** java List<String> vectorizeProperties = List.of("title", "content"); WeaviateClass docClass = WeaviateClass.builder() .className(className) .vectorizer("text2vec-ollama") .moduleConfig(Map.of( "text2vec-ollama", Map.of( "model", "bge-m3", "apiEndpoint", "http://host.docker.internal:11434", "vectorizeProperties", vectorizeProperties ) )) .properties(List.of(docId, title, content, unit)) .build(); client.schema().classCreator().withClass(docClass).run(); **Reproduction Steps** Deploy Weaviate via the above Docker Compose. Create schema with the above Java code. Restart Weaviate: Run a GraphQL query with .targetVectors(new String[]{ "title" }). **Observed** WeaviateErrorMessage(...): remote client vectorize: send POST request: Post "http://localhost:11434/api/embed": dial tcp 127.0.0.1:11434: connect: connection refused **Expected** Weaviate should use one of these custom endpoints for query-time embedding instead of defaulting to localhost:11434: Schema’s moduleConfig.text2vec-ollama.apiEndpoint Environment variable like TEXT2VEC_OLLAMA_API_ENDPOINT **Additional Notes** I have verified network connectivity from both host and container to http://host.docker.internal:11434/api/embed. No logs ever print my custom endpoint—Weaviate always seems unaware of it. Please advise how to properly override the default embedding endpoint for query-time text2vec-ollama. Thank you!

Best regards,

Mohamed Shahin
Weaviate Support Engineer
(Ireland, UTC±00:00/+01:00)

lssindustry4 · July 23, 2025, 4:37pm

Hi Mohamed,

Thank you for your response, this is a different issue but I have a similar issue as reported .

It always falls back to localhost:11434 during query- time .

Do you need any specifics ?

Best,

JC

Topic		Replies	Views
Query-time text2vec-ollama module ignores custom endpoint and always falls back to localhost:11434 General bug	1	134	June 17, 2025
Text2vec-ollama module ignores OLLAMA_API_ENDPOINT and defaults to localhost in Weaviate v1.31.2 on Linux Support python	4	115	June 30, 2025
Text2vec ollama embedding error Support	3	749	November 5, 2024
Ollama Embeddings call fails with wrong URL path: /api/embeddings Support integration , python	5	2296	November 6, 2024
[Question] Getting Weaviate and Ollama working together running locally Support technical	2	381	February 4, 2025

Current Status: Endpoint Ignored in text2vec-ollama Module

Related topics