diff --git a/packages/grafana-llm-app/llmclient/go.mod b/packages/grafana-llm-app/llmclient/go.mod
deleted file mode 100644
index a374de4c..00000000
--- a/packages/grafana-llm-app/llmclient/go.mod
+++ /dev/null
@@ -1,5 +0,0 @@
-module github.com/grafana/grafana-llm-app/llmclient
-
-go 1.19
-
-require github.com/sashabaranov/go-openai v1.15.3
diff --git a/packages/grafana-llm-app/llmclient/go.sum b/packages/grafana-llm-app/llmclient/go.sum
deleted file mode 100644
index c5e5edf6..00000000
--- a/packages/grafana-llm-app/llmclient/go.sum
+++ /dev/null
@@ -1,2 +0,0 @@
-github.com/sashabaranov/go-openai v1.15.3 h1:rzoNK9n+Cak+PM6OQ9puxDmFllxfnVea9StlmhglXqA=
-github.com/sashabaranov/go-openai v1.15.3/go.mod h1:lj5b/K+zjTSFxVLijLSTDZuP7adOgerWeFyZLUhAKRg=
diff --git a/packages/grafana-llm-app/llmclient/llmclient.go b/packages/grafana-llm-app/llmclient/llmclient.go
index a68ddd1d..fcd220f4 100644
--- a/packages/grafana-llm-app/llmclient/llmclient.go
+++ b/packages/grafana-llm-app/llmclient/llmclient.go
@@ -35,6 +35,12 @@ type ChatCompletionRequest struct {
 	Model Model `json:"model"`
 }
 
+// AssistantRequest is a request for creating an assistant using an abstract model.
+type AssistantRequest struct {
+	openai.AssistantRequest
+	Model Model `json:"model"`
+}
+
 // OpenAI is an interface for talking to OpenAI via the Grafana LLM app.
 // Requests made using this interface will be routed to the OpenAI backend
 // configured in the Grafana LLM app's settings, with authentication handled
@@ -47,6 +53,20 @@ type OpenAI interface {
 	ChatCompletions(ctx context.Context, req ChatCompletionRequest) (openai.ChatCompletionResponse, error)
 	// ChatCompletionsStream makes a streaming request to the OpenAI Chat Completion API.
 	ChatCompletionsStream(ctx context.Context, req ChatCompletionRequest) (*openai.ChatCompletionStream, error)
+	// CreateAssistant creates an assistant using the given request.
+	CreateAssistant(ctx context.Context, req AssistantRequest) (openai.Assistant, error)
+	// CreateThread creates a new thread.
+	CreateThread(ctx context.Context, req openai.ThreadRequest) (openai.Thread, error)
+	// CreateMessage creates a new message in a thread.
+	CreateMessage(ctx context.Context, threadID string, request openai.MessageRequest) (msg openai.Message, err error)
+	// CreateRun creates a new run in a thread.
+	CreateRun(ctx context.Context, threadID string, request openai.RunRequest) (run openai.Run, err error)
+	// RetrieveRun retrieves a run in a thread.
+	RetrieveRun(ctx context.Context, threadID string, runID string) (run openai.Run, err error)
+	// SubmitToolOutputs submits tool outputs for a run in a thread.
+	SubmitToolOutputs(ctx context.Context, threadID string, runID string, request openai.SubmitToolOutputsRequest) (response openai.Run, err error)
+	// ListMessage lists messages in a thread.
+	ListMessage(ctx context.Context, threadID string, limit *int, order *string, after *string, before *string) (openai.MessagesList, error)
 }
 
 type openAI struct {
@@ -159,3 +179,33 @@ func (o *openAI) ChatCompletionsStream(ctx context.Context, req ChatCompletionRe
 	r.Model = string(req.Model)
 	return o.client.CreateChatCompletionStream(ctx, r)
 }
+
+func (o *openAI) CreateAssistant(ctx context.Context, req AssistantRequest) (openai.Assistant, error) {
+	r := req.AssistantRequest
+	r.Model = string(req.Model)
+	return o.client.CreateAssistant(ctx, r)
+}
+
+func (o *openAI) CreateThread(ctx context.Context, req openai.ThreadRequest) (openai.Thread, error) {
+	return o.client.CreateThread(ctx, req)
+}
+
+func (o *openAI) CreateMessage(ctx context.Context, threadID string, request openai.MessageRequest) (msg openai.Message, err error) {
+	return o.client.CreateMessage(ctx, threadID, request)
+}
+
+func (o *openAI) CreateRun(ctx context.Context, threadID string, request openai.RunRequest) (run openai.Run, err error) {
+	return o.client.CreateRun(ctx, threadID, request)
+}
+
+func (o *openAI) RetrieveRun(ctx context.Context, threadID string, runID string) (run openai.Run, err error) {
+	return o.client.RetrieveRun(ctx, threadID, runID)
+}
+
+func (o *openAI) SubmitToolOutputs(ctx context.Context, threadID string, runID string, request openai.SubmitToolOutputsRequest) (response openai.Run, err error) {
+	return o.client.SubmitToolOutputs(ctx, threadID, runID, request)
+}
+
+func (o *openAI) ListMessage(ctx context.Context, threadID string, limit *int, order *string, after *string, before *string) (openai.MessagesList, error) {
+	return o.client.ListMessage(ctx, threadID, limit, order, after, before)
+}