feat: responses streaming added

Author: Pratham-Mishra04

core/providers/azure.go

@@ -369,7 +369,7 @@ func (provider *AzureProvider) ChatCompletionStream(ctx context.Context, postHoo
 	}
 
 	// Use shared streaming logic from OpenAI
-	return handleOpenAIStreaming(
+	return handleOpenAIChatCompletionStreaming(
 		ctx,
 		provider.streamClient,
 		fullURL,

core/providers/cerebras.go

@@ -136,7 +136,7 @@ func (provider *CerebrasProvider) Embedding(ctx context.Context, key schemas.Key
 // Returns a channel containing BifrostResponse objects representing the stream or an error if the request fails.
 func (provider *CerebrasProvider) ChatCompletionStream(ctx context.Context, postHookRunner schemas.PostHookRunner, key schemas.Key, request *schemas.BifrostChatRequest) (chan *schemas.BifrostStream, *schemas.BifrostError) {
 	// Use shared OpenAI-compatible streaming logic
-	return handleOpenAIStreaming(
+	return handleOpenAIChatCompletionStreaming(
 		ctx,
 		provider.streamClient,
 		provider.networkConfig.BaseURL+"/v1/chat/completions",

core/providers/gemini.go

@@ -177,7 +177,7 @@ func (provider *GeminiProvider) ChatCompletionStream(ctx context.Context, postHo
 	}
 
 	// Use shared OpenAI-compatible streaming logic
-	return handleOpenAIStreaming(
+	return handleOpenAIChatCompletionStreaming(
 		ctx,
 		provider.streamClient,
 		provider.networkConfig.BaseURL+"/openai/chat/completions",

core/providers/groq.go

@@ -176,7 +176,7 @@ func (provider *GroqProvider) Embedding(ctx context.Context, key schemas.Key, re
 // Returns a channel containing BifrostResponse objects representing the stream or an error if the request fails.
 func (provider *GroqProvider) ChatCompletionStream(ctx context.Context, postHookRunner schemas.PostHookRunner, key schemas.Key, request *schemas.BifrostChatRequest) (chan *schemas.BifrostStream, *schemas.BifrostError) {
 	// Use shared OpenAI-compatible streaming logic
-	return handleOpenAIStreaming(
+	return handleOpenAIChatCompletionStreaming(
 		ctx,
 		provider.streamClient,
 		provider.networkConfig.BaseURL+"/v1/chat/completions",

core/providers/mistral.go

@@ -130,7 +130,7 @@ func (provider *MistralProvider) Embedding(ctx context.Context, key schemas.Key,
 // Returns a channel containing BifrostResponse objects representing the stream or an error if the request fails.
 func (provider *MistralProvider) ChatCompletionStream(ctx context.Context, postHookRunner schemas.PostHookRunner, key schemas.Key, request *schemas.BifrostChatRequest) (chan *schemas.BifrostStream, *schemas.BifrostError) {
 	// Use shared OpenAI-compatible streaming logic
-	return handleOpenAIStreaming(
+	return handleOpenAIChatCompletionStreaming(
 		ctx,
 		provider.streamClient,
 		provider.networkConfig.BaseURL+"/v1/chat/completions",

core/providers/ollama.go

@@ -149,7 +149,7 @@ func (provider *OllamaProvider) Embedding(ctx context.Context, key schemas.Key,
 // Returns a channel containing BifrostResponse objects representing the stream or an error if the request fails.
 func (provider *OllamaProvider) ChatCompletionStream(ctx context.Context, postHookRunner schemas.PostHookRunner, key schemas.Key, request *schemas.BifrostChatRequest) (chan *schemas.BifrostStream, *schemas.BifrostError) {
 	// Use shared OpenAI-compatible streaming logic
-	return handleOpenAIStreaming(
+	return handleOpenAIChatCompletionStreaming(
 		ctx,
 		provider.streamClient,
 		provider.networkConfig.BaseURL+"/v1/chat/completions",