logs

BoundaryML · Jun 20, 2024 · b150672 · b150672
1 parent 6f7de88
commit b150672
Show file tree

Hide file tree

Showing 8 changed files with 17 additions and 97 deletions.
diff --git a/engine/baml-runtime/src/internal/llm_client/traits/mod.rs b/engine/baml-runtime/src/internal/llm_client/traits/mod.rs
@@ -9,7 +9,7 @@ pub use self::{
 };
 use super::{retry_policy::CallablePolicy, LLMResponse, ModelFeatures};
 use crate::{internal::prompt_renderer::PromptRenderer, RuntimeContext};
-use baml_types::{BamlMedia, BamlMediaType, BamlValue, MediaBase64, MediaUrl};
+use baml_types::{BamlMedia, BamlMediaType, BamlValue, MediaBase64};
 use base64::encode;
 use futures::stream::{StreamExt, TryStreamExt};
 use infer;
@@ -49,19 +49,13 @@ where
 {
     #[allow(async_fn_in_trait)]
     async fn single_call(&self, ctx: &RuntimeContext, prompt: &RenderedPrompt) -> LLMResponse {
-        log::info!("Starting stream");
         if self.model_features().resolve_media_urls {
-            log::info!("Resolving media URLs");
-
             if let RenderedPrompt::Chat(ref chat) = prompt {
-                log::info!("Processing chat prompt");
                 let messages_result = futures::stream::iter(chat.iter().map(|p| {
-                    log::info!("Processing chat message");
                     let new_parts = p
                         .parts
                         .iter()
                         .map(|part| async move {
-                            log::info!("Processing chat message part");
                             match part {
                                 ChatMessagePart::Image(BamlMedia::Url(_, media_url))
                                 | ChatMessagePart::Audio(BamlMedia::Url(_, media_url)) => {
@@ -120,23 +114,18 @@ where
                                         ))
                                     })
                                 }
-                                _ => {
-                                    log::info!("Processing text part");
-                                    Ok(part.clone())
-                                }
+                                _ => Ok(part.clone()),
                             }
                         })
                         .collect::<Vec<_>>();
                     async move {
-                        log::info!("Collecting new parts");
                         let new_parts = futures::stream::iter(new_parts)
                             .then(|f| f)
                             .collect::<Vec<_>>()
                             .await;
 
                         let new_parts = new_parts.into_iter().collect::<Result<Vec<_>, _>>()?;
 
-                        log::info!("Creating rendered chat message");
                         Ok::<_, anyhow::Error>(RenderedChatMessage {
                             role: p.role.clone(),
                             parts: new_parts,
@@ -152,23 +141,16 @@ where
                 let messages = match messages_result {
                     Ok(messages) => messages,
                     Err(e) => {
-                        log::error!("Error occurred: {}", e);
                         return LLMResponse::OtherFailure(format!("Error occurred: {}", e));
                     }
                 };
                 return self.chat(ctx, &messages).await;
             }
         }
-        log::info!("Processing prompt");
+
         match prompt {
-            RenderedPrompt::Chat(p) => {
-                log::info!("Streaming chat");
-                self.chat(ctx, p).await
-            }
-            RenderedPrompt::Completion(p) => {
-                log::info!("Streaming completion");
-                self.completion(ctx, p).await
-            }
+            RenderedPrompt::Chat(p) => self.chat(ctx, p).await,
+            RenderedPrompt::Completion(p) => self.completion(ctx, p).await,
         }
     }
 }
@@ -187,7 +169,6 @@ where
         let features = self.model_features();
 
         let prompt = renderer.render_prompt(ir, ctx, params, self.context())?;
-        log::debug!("WithPrompt.render_prompt => {:#?}", prompt);
 
         let mut prompt = match (features.completion, features.chat) {
             (true, false) => {
@@ -256,22 +237,16 @@ where
 {
     #[allow(async_fn_in_trait)]
     async fn stream(&self, ctx: &RuntimeContext, prompt: &RenderedPrompt) -> StreamResponse {
-        log::info!("Starting stream");
         if self.model_features().resolve_media_urls {
-            log::info!("Resolving media URLs");
-
             if let RenderedPrompt::Chat(ref chat) = prompt {
-                log::info!("Processing chat prompt");
                 let messages = futures::stream::iter(chat.iter().map(|p| {
-                    log::info!("Processing chat message");
                     let new_parts = p
                         .parts
                         .iter()
                         .map(|part| async move {
-                            log::info!("Processing chat message part");
                             match part {
-                                ChatMessagePart::Image(BamlMedia::Url(media_type, media_url))
-                                | ChatMessagePart::Audio(BamlMedia::Url(media_type, media_url)) => {
+                                ChatMessagePart::Image(BamlMedia::Url(_, media_url))
+                                | ChatMessagePart::Audio(BamlMedia::Url(_, media_url)) => {
                                     let mut base64 = "".to_string();
                                     let mut mime_type = "".to_string();
                                     if media_url.url.starts_with("data:") {
@@ -333,23 +308,18 @@ where
                                         ))
                                     })
                                 }
-                                _ => {
-                                    log::info!("Processing text part");
-                                    Ok(part.clone())
-                                }
+                                _ => Ok(part.clone()),
                             }
                         })
                         .collect::<Vec<_>>();
                     async move {
-                        log::info!("Collecting new parts");
                         let new_parts = futures::stream::iter(new_parts)
                             .then(|f| f)
                             .collect::<Vec<_>>()
                             .await;
 
                         let new_parts = new_parts.into_iter().collect::<Result<Vec<_>, _>>()?;
 
-                        log::info!("Creating rendered chat message");
                         Ok(RenderedChatMessage {
                             role: p.role.clone(),
                             parts: new_parts,
@@ -361,20 +331,14 @@ where
                 .await
                 .into_iter()
                 .collect::<Result<Vec<_>, _>>()?;
-                log::info!("Streaming chat");
+
                 return self.stream_chat(ctx, &messages).await;
             }
         }
-        log::info!("Processing prompt");
+
         match prompt {
-            RenderedPrompt::Chat(p) => {
-                log::info!("Streaming chat");
-                self.stream_chat(ctx, p).await
-            }
-            RenderedPrompt::Completion(p) => {
-                log::info!("Streaming completion");
-                self.stream_completion(ctx, p).await
-            }
+            RenderedPrompt::Chat(p) => self.stream_chat(ctx, p).await,
+            RenderedPrompt::Completion(p) => self.stream_completion(ctx, p).await,
         }
     }
 }
diff --git a/engine/baml-runtime/src/internal/prompt_renderer/mod.rs b/engine/baml-runtime/src/internal/prompt_renderer/mod.rs
@@ -6,7 +6,7 @@ use anyhow::Result;
 use baml_types::{BamlValue, FieldType};
 use internal_baml_core::{
     error_unsupported,
-    ir::{repr::IntermediateRepr, Expression, FunctionWalker, IRHelper},
+    ir::{repr::IntermediateRepr, FunctionWalker, IRHelper},
 };
 use internal_baml_jinja::{
     types::OutputFormatContent, RenderContext, RenderContext_Client, RenderedPrompt,

diff --git a/engine/baml-schema-wasm/src/runtime_wasm/mod.rs b/engine/baml-schema-wasm/src/runtime_wasm/mod.rs
@@ -561,7 +561,7 @@ fn get_dummy_value(
                     "{ url \"https://imgs.xkcd.com/comics/standards.png\"}".to_string()
                 }
                 baml_runtime::TypeValue::Audio => {
-                    "{ url \"https://www.soundjay.com/button/beep-07.wav\"}".to_string()
+                    "{ url \"https://actions.google.com/sounds/v1/emergency/beeper_emergency_call.ogg\"}".to_string()
                 }
             };
 

diff --git a/integ-tests/baml_src/clients.baml b/integ-tests/baml_src/clients.baml
@@ -71,7 +71,6 @@ client<llm> Gemini {
   options{
     model "gemini-1.5-pro-001"
     api_key env.GOOGLE_API_KEY
-    // default_role "user"
   }
 }
 

diff --git a/integ-tests/baml_src/test-files/functions/input/named-args/single/role.baml b/integ-tests/baml_src/test-files/functions/input/named-args/single/role.baml
diff --git a/integ-tests/python/baml_client/inlinedbaml.py b/integ-tests/python/baml_client/inlinedbaml.py
@@ -16,7 +16,7 @@
 
 file_map = {
 
-    "clients.baml": "retry_policy Bar {\n  max_retries 3\n  strategy {\n    type exponential_backoff\n  }\n}\n\nretry_policy Foo {\n  max_retries 3\n  strategy {\n    type constant_delay\n    delay_ms 100\n  }\n}\n\nclient<llm> GPT4 {\n  provider baml-openai-chat\n  options {\n    model gpt-4\n    api_key env.OPENAI_API_KEY\n  }\n} \n\n\nclient<llm> GPT4o {\n  provider baml-openai-chat\n  options {\n    model gpt-4o\n    api_key env.OPENAI_API_KEY\n  }\n} \n\n\nclient<llm> GPT4Turbo {\n  retry_policy Bar\n  provider baml-openai-chat\n  options {\n    model gpt-4-turbo\n    api_key env.OPENAI_API_KEY\n  }\n} \n\nclient<llm> GPT35 {\n  provider baml-openai-chat\n  options {\n    model \"gpt-3.5-turbo\"\n    api_key env.OPENAI_API_KEY\n  }\n}\n\nclient<llm> Ollama {\n  provider ollama\n  options {\n    model llama2\n  }\n}\n\nclient<llm> GPT35Azure {\n  provider azure-openai\n  options {\n    resource_name \"west-us-azure-baml\"\n    deployment_id \"gpt-35-turbo-default\"\n    // base_url \"https://west-us-azure-baml.openai.azure.com/openai/deployments/gpt-35-turbo-default\"\n    api_version \"2024-02-01\"\n    api_key env.AZURE_OPENAI_API_KEY\n  }\n}\n\nclient<llm> Gemini {\n  provider google-ai\n  options{\n    model \"gemini-1.5-pro-001\"\n    api_key env.GOOGLE_API_KEY\n    // default_role \"user\"\n  }\n}\n\n\nclient<llm> Claude {\n  provider anthropic\n  options {\n    model claude-3-haiku-20240307\n    api_key env.ANTHROPIC_API_KEY\n    max_tokens 1000\n  }\n}\n\nclient<llm> Resilient_SimpleSyntax {\n  retry_policy Foo\n  provider baml-fallback\n  options {\n    strategy [\n      GPT4Turbo\n      GPT35\n      Lottery_SimpleSyntax\n    ]\n  }\n} \n \nclient<llm> Lottery_SimpleSyntax {\n  provider baml-round-robin\n  options {\n    start 0\n    strategy [\n      GPT35\n      Claude\n    ]\n  }\n}\n",
+    "clients.baml": "retry_policy Bar {\n  max_retries 3\n  strategy {\n    type exponential_backoff\n  }\n}\n\nretry_policy Foo {\n  max_retries 3\n  strategy {\n    type constant_delay\n    delay_ms 100\n  }\n}\n\nclient<llm> GPT4 {\n  provider baml-openai-chat\n  options {\n    model gpt-4\n    api_key env.OPENAI_API_KEY\n  }\n} \n\n\nclient<llm> GPT4o {\n  provider baml-openai-chat\n  options {\n    model gpt-4o\n    api_key env.OPENAI_API_KEY\n  }\n} \n\n\nclient<llm> GPT4Turbo {\n  retry_policy Bar\n  provider baml-openai-chat\n  options {\n    model gpt-4-turbo\n    api_key env.OPENAI_API_KEY\n  }\n} \n\nclient<llm> GPT35 {\n  provider baml-openai-chat\n  options {\n    model \"gpt-3.5-turbo\"\n    api_key env.OPENAI_API_KEY\n  }\n}\n\nclient<llm> Ollama {\n  provider ollama\n  options {\n    model llama2\n  }\n}\n\nclient<llm> GPT35Azure {\n  provider azure-openai\n  options {\n    resource_name \"west-us-azure-baml\"\n    deployment_id \"gpt-35-turbo-default\"\n    // base_url \"https://west-us-azure-baml.openai.azure.com/openai/deployments/gpt-35-turbo-default\"\n    api_version \"2024-02-01\"\n    api_key env.AZURE_OPENAI_API_KEY\n  }\n}\n\nclient<llm> Gemini {\n  provider google-ai\n  options{\n    model \"gemini-1.5-pro-001\"\n    api_key env.GOOGLE_API_KEY\n  }\n}\n\n\nclient<llm> Claude {\n  provider anthropic\n  options {\n    model claude-3-haiku-20240307\n    api_key env.ANTHROPIC_API_KEY\n    max_tokens 1000\n  }\n}\n\nclient<llm> Resilient_SimpleSyntax {\n  retry_policy Foo\n  provider baml-fallback\n  options {\n    strategy [\n      GPT4Turbo\n      GPT35\n      Lottery_SimpleSyntax\n    ]\n  }\n} \n \nclient<llm> Lottery_SimpleSyntax {\n  provider baml-round-robin\n  options {\n    start 0\n    strategy [\n      GPT35\n      Claude\n    ]\n  }\n}\n",
     "fiddle-examples/chain-of-thought.baml": "class Email {\n    subject string\n    body string\n    from_address string\n}\n\nenum OrderStatus {\n    ORDERED\n    SHIPPED\n    DELIVERED\n    CANCELLED\n}\n\nclass OrderInfo {\n    order_status OrderStatus\n    tracking_number string?\n    estimated_arrival_date string?\n}\n\nfunction GetOrderInfo(email: Email) -> OrderInfo {\n  client GPT4\n  prompt #\"\n    Given the email below:\n\n    ```\n    from: {{email.from_address}}\n    Email Subject: {{email.subject}}\n    Email Body: {{email.body}}\n    ```\n\n    Extract this info from the email in JSON format:\n    {{ ctx.output_format }}\n\n    Before you output the JSON, please explain your\n    reasoning step-by-step. Here is an example on how to do this:\n    'If we think step by step we can see that ...\n     therefore the output JSON is:\n    {\n      ... the json schema ...\n    }'\n  \"#\n}",
     "fiddle-examples/chat-roles.baml": "// This will be available as an enum in your Python and Typescript code.\nenum Category2 {\n    Refund\n    CancelOrder\n    TechnicalSupport\n    AccountIssue\n    Question\n}\n\nfunction ClassifyMessage2(input: string) -> Category {\n  client GPT4\n\n  prompt #\"\n    {{ _.role(\"system\") }}\n    // You can use _.role(\"system\") to indicate that this text should be a system message\n\n    Classify the following INPUT into ONE\n    of the following categories:\n\n    {{ ctx.output_format }}\n\n    {{ _.role(\"user\") }}\n    // And _.role(\"user\") to indicate that this text should be a user message\n\n    INPUT: {{ input }}\n\n    Response:\n  \"#\n}",
     "fiddle-examples/classify-message.baml": "// This will be available as an enum in your Python and Typescript code.\nenum Category {\n    Refund\n    CancelOrder\n    TechnicalSupport\n    AccountIssue\n    Question\n}\n\nfunction ClassifyMessage(input: string) -> Category {\n  client GPT4\n\n  prompt #\"\n    Classify the following INPUT into ONE\n    of the following categories:\n\n    INPUT: {{ input }}\n\n    {{ ctx.output_format }}\n\n    Response:\n  \"#\n}",