diff --git a/Cargo.lock b/Cargo.lock index 959825d..37523aa 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -335,15 +335,6 @@ dependencies = [ "tokio", ] -[[package]] -name = "async-convert" -version = "1.0.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "6d416feee97712e43152cd42874de162b8f9b77295b1c85e5d92725cc8310bae" -dependencies = [ - "async-trait", -] - [[package]] name = "async-executor" version = "1.13.2" @@ -431,30 +422,41 @@ dependencies = [ [[package]] name = "async-openai" -version = "0.24.1" +version = "0.29.3" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "c6db3286b4f52b6556ac5208fb575d035eca61a2bf40d7e75d1db2733ffc599f" +checksum = "d4fc47ec9e669d562e0755f59e1976d157546910e403f3c2da856d0a4d3cdc07" dependencies = [ - "async-convert", + "async-openai-macros", "backoff", "base64 0.22.1", "bytes", "derive_builder", "eventsource-stream", "futures", - "rand 0.8.5", + "rand 0.9.1", "reqwest", "reqwest-eventsource", "secrecy", "serde", "serde_json", - "thiserror 1.0.69", + "thiserror 2.0.12", "tokio", "tokio-stream", "tokio-util", "tracing", ] +[[package]] +name = "async-openai-macros" +version = "0.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0289cba6d5143bfe8251d57b4a8cac036adf158525a76533a7082ba65ec76398" +dependencies = [ + "proc-macro2", + "quote", + "syn 2.0.101", +] + [[package]] name = "async-recursion" version = "1.1.1" @@ -5011,9 +5013,9 @@ checksum = "1c107b6f4780854c8b126e228ea8869f4d7b71260f962fefb57b996b8959ba6b" [[package]] name = "secrecy" -version = "0.8.0" +version = "0.10.3" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "9bd1c54ea06cfd2f6b63219704de0b9b4f72dcc2b8fdef820be6cd799780e91e" +checksum = "e891af845473308773346dc847b2c23ee78fe442e0472ac50e22a18a93d3ae5a" dependencies = [ "serde", "zeroize", diff --git a/Cargo.toml b/Cargo.toml index a2cebe1..24ca537 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -12,7 +12,7 @@ resolver = "2" [workspace.dependencies] anyhow = "1.0.94" -async-openai = "0.24.1" +async-openai = "0.29.3" async-stream = "0.3.6" async-trait = "0.1.88" axum-htmx = "0.7.0" diff --git a/composite-retrieval/src/answer_retrieval.rs b/composite-retrieval/src/answer_retrieval.rs index be705c0..64c3782 100644 --- a/composite-retrieval/src/answer_retrieval.rs +++ b/composite-retrieval/src/answer_retrieval.rs @@ -154,8 +154,6 @@ pub fn create_chat_request( CreateChatCompletionRequestArgs::default() .model(&settings.query_model) - .temperature(0.2) - .max_tokens(3048u32) .messages([ ChatCompletionRequestSystemMessage::from(settings.query_system_prompt.clone()).into(), ChatCompletionRequestUserMessage::from(user_message).into(), diff --git a/composite-retrieval/src/graph.rs b/composite-retrieval/src/graph.rs index fa22ba4..24bd9ea 100644 --- a/composite-retrieval/src/graph.rs +++ b/composite-retrieval/src/graph.rs @@ -1,5 +1,4 @@ use surrealdb::Error; -use tracing::debug; use common::storage::{db::SurrealDbClient, types::knowledge_entity::KnowledgeEntity}; @@ -57,8 +56,6 @@ pub async fn find_entities_by_relationship_by_id( entity_id ); - debug!("{}", query); - db.query(query).await?.take(0) } diff --git a/ingestion-pipeline/src/enricher.rs b/ingestion-pipeline/src/enricher.rs index 8eb918d..e2fc811 100644 --- a/ingestion-pipeline/src/enricher.rs +++ b/ingestion-pipeline/src/enricher.rs @@ -110,8 +110,6 @@ impl IngestionEnricher { let request = CreateChatCompletionRequestArgs::default() .model(&settings.processing_model) - .temperature(0.2) - .max_tokens(6048u32) .messages([ ChatCompletionRequestSystemMessage::from(INGRESS_ANALYSIS_SYSTEM_MESSAGE).into(), ChatCompletionRequestUserMessage::from(user_message).into(), diff --git a/ingestion-pipeline/src/utils/image_parsing.rs b/ingestion-pipeline/src/utils/image_parsing.rs index ac97878..1b3295e 100644 --- a/ingestion-pipeline/src/utils/image_parsing.rs +++ b/ingestion-pipeline/src/utils/image_parsing.rs @@ -23,7 +23,6 @@ pub async fn extract_text_from_image( let request = CreateChatCompletionRequestArgs::default() .model(system_settings.image_processing_model) - .max_tokens(6400_u32) .messages([ChatCompletionRequestUserMessageArgs::default() .content(vec![ ChatCompletionRequestMessageContentPartTextArgs::default() diff --git a/ingestion-pipeline/src/utils/pdf_ingestion.rs b/ingestion-pipeline/src/utils/pdf_ingestion.rs index 62d8b57..9ee1688 100644 --- a/ingestion-pipeline/src/utils/pdf_ingestion.rs +++ b/ingestion-pipeline/src/utils/pdf_ingestion.rs @@ -334,12 +334,10 @@ async fn vision_markdown( let request = CreateChatCompletionRequestArgs::default() .model(settings.image_processing_model.clone()) - .temperature(0.0) .messages([ChatCompletionRequestUserMessageArgs::default() .content(content_parts) .build()? .into()]) - .max_tokens(16400_u32) .build()?; let response = client.chat().create(request).await?;