diff --git a/how-to/configure-embedding-models/index.html b/how-to/configure-embedding-models/index.html index fecfab12..5bd96581 100644 --- a/how-to/configure-embedding-models/index.html +++ b/how-to/configure-embedding-models/index.html @@ -1311,7 +1311,7 @@

Install BAAI/bge-smal 
helm install kubeai-models kubeai/models -f ./kubeai-models.yaml

Once the pod is ready, you can use the OpenAI Python SDK to interact with the model:

-
from openai import OpenAI
+
from openai import OpenAI
 # Assumes port-forward of kubeai service to localhost:8000.
 client = OpenAI(api_key="ignored", base_url="http://localhost:8000/openai/v1")
 response = client.embeddings.create(
diff --git a/how-to/configure-text-generation-models/index.html b/how-to/configure-text-generation-models/index.html
index 4b504d45..d29991bd 100644
--- a/how-to/configure-text-generation-models/index.html
+++ b/how-to/configure-text-generation-models/index.html
@@ -1512,8 +1512,8 @@ 
Using the OpenAI
 
Once the pod is ready, you can use the OpenAI Python SDK to interact with the model:
 All OpenAI SDKs work with KubeAI since the KubeAI service is OpenAI API compatible.

 
See the below example code to interact with the model using the OpenAI Python SDK:
-
import os
-from openai import OpenAI
+
import os
+from openai import OpenAI
 # Assumes port-forward of kubeai service to localhost:8000.
 kubeai_endpoint = "http://localhost:8000/openai/v1"
 model_name = "llama-3.1-8b-instruct-fp8-l4"
diff --git a/reference/openai-api-compatibility/index.html b/reference/openai-api-compatibility/index.html
index 94203298..bce131a6 100644
--- a/reference/openai-api-compatibility/index.html
+++ b/reference/openai-api-compatibility/index.html
@@ -1452,7 +1452,7 @@ 
OpenAI Client libariesYou can use the official OpenAI client libraries by setting the
 base_url to the KubeAI endpoint.

 
For example, you can use the Python client like this:
-
from openai import OpenAI
+
from openai import OpenAI
 client = OpenAI(api_key="ignored",
                 base_url="http://kubeai/openai/v1")
 response = client.chat.completions.create(
diff --git a/sitemap.xml b/sitemap.xml
index cab9947a..dbd7df05 100644
--- a/sitemap.xml
+++ b/sitemap.xml
@@ -2,130 +2,130 @@
 
     
          https://www.kubeai.org/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/benchmarks/llama-3.2-11b-vision/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/concepts/autoscaling/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/concepts/backend-servers/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/concepts/load-balancing/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/concepts/lora-adapters/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/concepts/resource-profiles/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/concepts/storage-caching/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/contributing/development-environment/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/contributing/documentation/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/contributing/release-process/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/how-to/architect-for-multitenancy/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/how-to/authenticate-to-model-repos/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/how-to/build-models-into-containers/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/how-to/cache-models-with-aws-efs/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/how-to/cache-models-with-gcp-filestore/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/how-to/configure-autoscaling/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/how-to/configure-embedding-models/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/how-to/configure-resource-profiles/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/how-to/configure-speech-to-text/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/how-to/configure-text-generation-models/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/how-to/install-models/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/how-to/serve-lora-adapters/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/installation/any/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/installation/eks/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/installation/gke/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/reference/kubernetes-api/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/reference/openai-api-compatibility/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/tutorials/langchain/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/tutorials/langtrace/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/tutorials/private-deep-chat/
-         2025-01-03
+         2025-01-11
     
     
          https://www.kubeai.org/tutorials/weaviate/
-         2025-01-03
+         2025-01-11
     
 
\ No newline at end of file
diff --git a/sitemap.xml.gz b/sitemap.xml.gz
index b018c366..127c07ac 100644
Binary files a/sitemap.xml.gz and b/sitemap.xml.gz differ
diff --git a/tutorials/langchain/index.html b/tutorials/langchain/index.html
index 1b467753..1bd4a902 100644
--- a/tutorials/langchain/index.html
+++ b/tutorials/langchain/index.html
@@ -1364,7 +1364,7 @@ 
Using LangChain
from langchain_openai import ChatOpenAI
+
from langchain_openai import ChatOpenAI
 
 llm = ChatOpenAI(
     model="gemma2-2b-cpu",
diff --git a/tutorials/langtrace/index.html b/tutorials/langtrace/index.html
index bb1eda0b..a5c0538d 100644
--- a/tutorials/langtrace/index.html
+++ b/tutorials/langtrace/index.html
@@ -1283,11 +1283,11 @@ 
Deploying KubeAI with Langtrace
# Replace this with your langtrace API key by visiting http://localhost:3000
 langtrace_api_key="f7e003de19b9a628258531c17c264002e985604ca9fa561debcc85c41f357b09"
 
-from langtrace_python_sdk import langtrace
-from langtrace_python_sdk.utils.with_root_span import with_langtrace_root_span
+from langtrace_python_sdk import langtrace
+from langtrace_python_sdk.utils.with_root_span import with_langtrace_root_span
 # Paste this code after your langtrace init function
 
-from openai import OpenAI
+from openai import OpenAI
 
 langtrace.init(
     api_key=api_key,
@@ -1298,7 +1298,7 @@ 
Deploying KubeAI with Langtracemodel = "gemma2-2b-cpu"
 
 @with_langtrace_root_span()
-def example():
+def example():
     client = OpenAI(base_url=base_url, api_key="ignored-by-kubeai")
     response = client.chat.completions.create(
         model=model,
diff --git a/tutorials/weaviate/index.html b/tutorials/weaviate/index.html
index 453ab289..d09dbf1b 100644
--- a/tutorials/weaviate/index.html
+++ b/tutorials/weaviate/index.html
@@ -1561,10 +1561,10 @@ 
Weaviate client Python SetupCollection and Data Import

 
Create a file named create-collection.py with the following content:
-
import json
-import weaviate
-import requests
-from weaviate.classes.config import Configure
+
import json
+import weaviate
+import requests
+from weaviate.classes.config import Configure
 
 # This works due to port forward in previous step
 with weaviate.connect_to_local(port=8080, grpc_port=50051) as client:
@@ -1604,8 +1604,8 @@ 
Collection and Data ImportSemantic Search

 
Now let's do semantic search, which uses the embeddings. Create a file named search.py with the following content:
-
import weaviate
-from weaviate.classes.config import Configure
+
import weaviate
+from weaviate.classes.config import Configure
 
 # This works due to port forward in previous step
 with weaviate.connect_to_local(port=8080, grpc_port=50051) as client:
@@ -1630,8 +1630,8 @@ 
Generative Search (RAG)Now let's do generative search, which uses the generative model (Text generation LLM).
 The generative model is run locally and managed by KubeAI.

 
Create a file named generate.py with the following content:
-
import weaviate
-from weaviate.classes.config import Configure
+
import weaviate
+from weaviate.classes.config import Configure
 
 # This works due to port forward in previous step
 with weaviate.connect_to_local(port=8080, grpc_port=50051) as client: