(Wait for py client release to merge) 20250804 Add model2vec examples

docs/deploy/configuration/env-vars/index.md

@@ -51,7 +51,7 @@ import APITable from '@site/src/components/APITable';
 | `GRPC_PORT` | The port on which Weaviate's gRPC server listens for incoming requests. Default: `50051` | `string - number` | `50052` |
 | `LIMIT_RESOURCES` | If `true`, Weaviate will automatically attempt to auto-detect and limit the amount of resources (memory & threads) it uses to (0.8 * total memory) and (number of cores-1). It will override any `GOMEMLIMIT` values, however it will respect `GOMAXPROCS` values. | `boolean` | `false` |
 | `LOG_FORMAT` | Set the Weaviate logging format <br/><br/>Default: Outputs log data to json. e.g.: `{"action":"startup","level":"debug","msg":"finished initializing modules","time":"2023-04-12T05:07:43Z"}` <br/>`text`: Outputs log data to a string. e.g. `time="2023-04-12T04:54:23Z" level=debug msg="finished initializing modules" action=startup` | `string` |  |
-| `LOG_LEVEL` | Sets the Weaviate logging level. Default: `info`<br/><br/>`panic`: Panic entries only. (new in `v1.24`) <br/>`fatal`: Fatal entries only. (new in `v1.24`)  <br/> `error`: Error entries only. (new in `v1.24`) <br/>`warning`: Warning entries only. (new in `v1.24`) <br/>`info`: General operational entries. <br/> `debug`: Very verbose logging. <br/>`trace`: Even finer-grained informational events than `debug`. | `string` | | 
+| `LOG_LEVEL` | Sets the Weaviate logging level. Default: `info`<br/><br/>`panic`: Panic entries only. (new in `v1.24`) <br/>`fatal`: Fatal entries only. (new in `v1.24`)  <br/> `error`: Error entries only. (new in `v1.24`) <br/>`warning`: Warning entries only. (new in `v1.24`) <br/>`info`: General operational entries. <br/> `debug`: Very verbose logging. <br/>`trace`: Even finer-grained informational events than `debug`. | `string` | |
 | `MAXIMUM_ALLOWED_COLLECTIONS_COUNT` | Maximum allowed number of collections in a Weaviate node. A value of `-1` removes the limit. Default: `1000` <br/><br/>Instead of raising the collections count limit, consider [rethinking your architecture](/weaviate/starter-guides/managing-collections/collections-scaling-limits.mdx).<br/>Added in `v1.30`| `string - number` | `20` |
 | `MEMORY_READONLY_PERCENTAGE` | If memory usage is higher than the given percentage all shards on the affected node will be marked as `READONLY`, meaning all future write requests will fail. (Default: `0` - i.e. no limit) | `string - number` | `75` |
 | `MEMORY_WARNING_PERCENTAGE` | If memory usage is higher than the given percentage a warning will be logged by all shards on the affected node's disk. (Default: `0` - i.e. no limit) | `string - number` | `85` |
@@ -105,7 +105,7 @@ import APITable from '@site/src/components/APITable';
 | `OFFLOAD_S3_BUCKET_AUTO_CREATE` | Whether to automatically create the S3 bucket for offloading if it does not exist (default: `false`) | `boolean` | `true` |
 | `OFFLOAD_S3_CONCURRENCY` | The maximum number of parts that will be uploaded/downloaded in parallel during offloading operations (default: `25`) | `string - number` | `10` |
 | `OFFLOAD_TIMEOUT` | The request timeout value, in seconds (default: `120`) | `string - number` | `60` |
-| `TRANSFORMERS_INFERENCE_API` | The endpoint where to reach the transformers module if enabled | `string` | `http://t2v-transformers:8080` |
+| `TRANSFORMERS_INFERENCE_API` | The endpoint where to reach the transformers module if enabled | `string` | `http://text2vec-transformers:8080` |
 | `USE_GOOGLE_AUTH` | Automatically look for Google Cloud credentials, and generate Vertex AI access tokens for Weaviate to use as needed ([read more](/weaviate/model-providers/google/index.md)). (default: `false`) | `boolean` | `true` |
 | `USE_SENTENCE_TRANSFORMERS_VECTORIZER` | (EXPERIMENTAL) Use the `sentence-transformer` vectorizer instead of the default vectorizer (from the `transformers` library). Applies to custom images only. | `boolean` | `true` |
 | `CLIP_WAIT_FOR_STARTUP` | If `true`, Weaviate waits for the `multi2vec-clip` module to start up before starting (default: `true`).  | `boolean` | `true` |

docs/deploy/installation-guides/docker-installation.md

@@ -78,7 +78,7 @@ volumes:
 ```
 
 :::caution
-Anonymous access is strongly discouraged except for development or evaluation purposes. 
+Anonymous access is strongly discouraged except for development or evaluation purposes.
 :::
 
   </TabItem>
@@ -225,9 +225,9 @@ services:
       PERSISTENCE_DATA_PATH: "./data"
       DEFAULT_VECTORIZER_MODULE: text2vec-transformers
       ENABLE_MODULES: text2vec-transformers
-      TRANSFORMERS_INFERENCE_API: http://t2v-transformers:8080
+      TRANSFORMERS_INFERENCE_API: http://text2vec-transformers:8080
       CLUSTER_HOSTNAME: 'node1'
-  t2v-transformers:
+  text2vec-transformers:
     image: cr.weaviate.io/semitechnologies/transformers-inference:sentence-transformers-multi-qa-MiniLM-L6-cos-v1
     environment:
       ENABLE_CUDA: 0 # set to 1 to enable

docs/weaviate/model-providers/_includes/provider.vectorizer.py

@@ -1476,6 +1476,47 @@
 # clean up
 client.collections.delete("DemoCollection")
 
+# START BasicVectorizerModel2Vec
+from weaviate.classes.config import Configure
+
+client.collections.create(
+    "DemoCollection",
+    # highlight-start
+    vector_config=[
+        Configure.Vectors.text2vec_model2vec(
+            name="title_vector",
+            source_properties=["title"],
+        )
+    ],
+    # highlight-end
+    # Additional parameters not shown
+)
+# END BasicVectorizerModel2Vec
+
+# clean up
+client.collections.delete("DemoCollection")
+
+# START FullVectorizerModel2Vec
+from weaviate.classes.config import Configure
+
+client.collections.create(
+    "DemoCollection",
+    # highlight-start
+    vector_config=[
+        Configure.Vectors.text2vec_model2vec(
+            name="title_vector",
+            source_properties=["title"],
+            inference_url="<custom-inference-url>",  # Default - configuration defined through container, e.g. Docker compose file
+        )
+    ],
+    # highlight-end
+    # Additional parameters not shown
+)
+# END FullVectorizerModel2Vec
+
+# clean up
+client.collections.delete("DemoCollection")
+
 # START BasicMMVectorizerCLIP
 from weaviate.classes.config import Configure, DataType, Multi2VecField, Property
 

docs/weaviate/model-providers/_includes/provider.vectorizer.ts

@@ -7,7 +7,7 @@ import weaviate from 'weaviate-client';
 
 async function main() {
 
-  
+
 const client = await weaviate.connectToLocal({
   headers: {
     'X-OpenAI-Api-Key': process.env.OPENAI_APIKEY || '',
@@ -727,7 +727,7 @@ await client.collections.delete('DemoCollection');
 // START BasicColBERTVectorizerJinaAI
 await client.collections.create({
   name: 'DemoCollection',
-  vectorizers: [ 
+  vectorizers: [
     weaviate.configure.multiVectors.text2VecJinaAI({
       name: 'title_vector',
       sourceProperties: ['title'],
@@ -742,7 +742,7 @@ await client.collections.delete('DemoCollection');
 // START ColBERTVectorizerJinaCustomModel
 await client.collections.create({
   name: 'DemoCollection',
-  vectorizers: [ 
+  vectorizers: [
     weaviate.configure.multiVectors.text2VecJinaAI({
       name: 'title_vector',
       sourceProperties: ['title'],
@@ -758,7 +758,7 @@ await client.collections.delete('DemoCollection');
 // START FullColBERTVectorizerJinaAI
 await client.collections.create({
   name: 'DemoCollection',
-  vectorizers: [ 
+  vectorizers: [
     weaviate.configure.multiVectors.text2VecJinaAI({
       name: 'title_vector',
       sourceProperties: ['title'],
@@ -825,7 +825,7 @@ await client.collections.delete('DemoCollection');
 // START BasicVectorizerNVIDIA
 await client.collections.create({
   name: 'DemoCollection',
-  vectorizers: [ 
+  vectorizers: [
     weaviate.configure.vectors.text2VecNvidia({
       name: 'title_vector',
       sourceProperties: ['title'],
@@ -841,7 +841,7 @@ await client.collections.delete('DemoCollection');
 // START VectorizerNVIDIACustomModel
 await client.collections.create({
   name: 'DemoCollection',
-  vectorizers: [ 
+  vectorizers: [
     weaviate.configure.vectors.text2VecNvidia({
       name: 'title_vector',
       sourceProperties: ['title'],
@@ -858,7 +858,7 @@ await client.collections.delete('DemoCollection');
 // START FullVectorizerNVIDIA
 await client.collections.create({
   name: 'DemoCollection',
-  vectorizers: [ 
+  vectorizers: [
     weaviate.configure.vectors.text2VecNvidia({
       name: 'title_vector',
       sourceProperties: ['title'],
@@ -1587,6 +1587,17 @@ await client.collections.create({
 });
 // END FullVectorizerGPT4All
 
+// START BasicVectorizerModel2Vec
+// Coming soon
+// END BasicVectorizerModel2Vec
+
+// Clean up
+await client.collections.delete('DemoCollection');
+
+// START FullVectorizerModel2Vec
+// Coming soon
+// END FullVectorizerModel2Vec
+
 // START BasicMMVectorizerCLIP
 await client.collections.create({
   name: 'DemoCollection',
@@ -1852,4 +1863,4 @@ client.close();
 
 }
 
-void main();
+void main();

docs/weaviate/model-providers/gpt4all/embeddings.md

@@ -73,12 +73,12 @@ services:
     # Other Weaviate configuration
     environment:
       GPT4ALL_INFERENCE_API: http://text2vec-gpt4all:8080  # Set the inference API endpoint
-  t2v-gpt4all:  # Set the name of the inference container
+  text2vec-gpt4all:  # Set the name of the inference container
     image: cr.weaviate.io/semitechnologies/gpt4all-inference:all-MiniLM-L6-v2
 ```
 
 - `GPT4ALL_INFERENCE_API` environment variable sets the inference API endpoint
-- `t2v-gpt4all` is the name of the inference container
+- `text2vec-gpt4all` is the name of the inference container
 - `image` is the container image
 
 </TabItem>

docs/weaviate/model-providers/index.md

@@ -53,6 +53,7 @@ Read more about [enabling all API-based modules](../configuration/modules.md#ena
 | --- | --- | --- | --- |
 | [GPT4All](./gpt4all/index.md) | [Text](./gpt4all/embeddings.md) | - | - |
 | [Hugging Face](./transformers/index.md) | [Text](./transformers/embeddings.md), [Multimodal (CLIP)](./transformers/embeddings-multimodal.md) | - | [Reranker](./transformers/reranker.md) |
+| [Model2vec](./model2vec/index.md) | [Text](./model2vec/embeddings.md) | - | - |
 | [Meta ImageBind](./imagebind/index.md) | [Multimodal](./imagebind/embeddings-multimodal.md) | - | - |
 | [Ollama](./ollama/index.md) | [Text](./ollama/embeddings.md) | [Text](./ollama/generative.md) | - |
 

docs/weaviate/model-providers/model2vec/_category_.json

@@ -0,0 +1,4 @@
+{
+    "label": "GPT4All (locally hosted)",
+    "position": 320
+}