Solr example: use Hugging face embeddings (LangStream#729)

examples/applications/query-solr/chatbot.yaml

@@ -32,7 +32,9 @@ pipeline:
   - name: "compute-embeddings"
     type: "compute-ai-embeddings"
     configuration:
-      model: "${secrets.open-ai.embeddings-model}" # This needs to match the name of the model deployment, not the base model
+      ai-service: "huggingface"
+      model: "multilingual-e5-small"
+      model-url: "djl://ai.djl.huggingface.pytorch/intfloat/multilingual-e5-small"
       embeddings-field: "value.question_embeddings"
       text: "{{ value.question }}"
       flush-interval: 0
@@ -51,6 +53,7 @@ pipeline:
     type: "ai-chat-completions"
 
     configuration:
+      ai-service: "openai"
       model: "${secrets.open-ai.chat-completions-model}" # This needs to be set to the model deployment name, not the base name
       # on the log-topic we add a field with the answer
       completion-field: "value.answer"

examples/applications/query-solr/configuration.yaml

@@ -19,10 +19,16 @@ configuration:
   resources:
   - type: "open-ai-configuration"
     name: "OpenAI Azure configuration"
+    id: "openai"
     configuration:
       url: "${secrets.open-ai.url}"
       access-key: "${secrets.open-ai.access-key}"
       provider: "${secrets.open-ai.provider}"
+  - type: "hugging-face-configuration"
+    name: "Hugging Face AI configuration"
+    id: "huggingface"
+    configuration:
+      provider: "local"
   - type: "vector-database"
     name: "SolrDataSource"
     configuration:

examples/applications/query-solr/crawler.yaml

@@ -40,7 +40,7 @@ assets:
              "add-field-type" : {
                    "name": "knn_vector",
                    "class": "solr.DenseVectorField",
-                   "vectorDimension": "1536",
+                   "vectorDimension": "384",
                    "similarityFunction": "cosine"
               }
              }
@@ -108,10 +108,10 @@ pipeline:
     type: "text-splitter"
     configuration:
       splitter_type: "RecursiveCharacterTextSplitter"
-      chunk_size: 400
+      chunk_size: 200
       separators: ["\n\n", "\n", " ", ""]
       keep_separator: false
-      chunk_overlap: 100
+      chunk_overlap: 20
       length_function: "cl100k_base"
   - name: "Convert to structured data"
     type: "document-to-json"
@@ -133,7 +133,9 @@ pipeline:
     type: "compute-ai-embeddings"
     output: chunks-topic
     configuration:
-      model: "text-embedding-ada-002" # This needs to match the name of the model deployment, not the base model
+      ai-service: "huggingface"
+      model: "multilingual-e5-small"
+      model-url: "djl://ai.djl.huggingface.pytorch/intfloat/multilingual-e5-small"
       embeddings-field: "value.embeddings_vector"
       text: "{{ value.text }}"
       batch-size: 10