trim leading/trailing whitespace (#74)

* trim leading/trailing whitespace

* bump ver

* add missing migration

Author: ChuckHend

Cargo.lock

@@ -1,6 +1,6 @@
 [package]
 name = "vectorize"
-version = "0.12.0"
+version = "0.12.1"
 edition = "2021"
 publish = false
 

Cargo.toml

@@ -6,7 +6,7 @@ description = "The simplest way to orchestrate vector search on Postgres."
 homepage = "https://github.com/tembo-io/pg_vectorize"
 documentation = "https://github.com/tembo-io/pg_vectorize"
 categories = ["orchestration", "machine_learning"]
-version = "0.12.0"
+version = "0.12.1"
 
 [build]
 postgres_version = "15"

Trunk.toml

@@ -248,7 +248,7 @@ pub async fn get_new_updates(
                     let token_estimate = bpe.encode_with_special_tokens(&ipt).len() as i32;
                     new_inputs.push(Inputs {
                         record_id: r.get("record_id"),
-                        inputs: ipt,
+                        inputs: ipt.trim().to_owned(),
                         token_estimate,
                     })
                 }

sql/vectorize--0.12.0--0.12.1.sql

@@ -33,7 +33,7 @@ fn _handle_table_update(job_name: &str, record_ids: Vec<String>, inputs: Vec<Str
         let token_estimate = bpe.encode_with_special_tokens(&input).len() as i32;
         new_inputs.push(Inputs {
             record_id,
-            inputs: input,
+            inputs: input.trim().to_owned(),
             token_estimate,
         })
     }
@@ -138,7 +138,7 @@ pub fn initalize_table_job(
                 record_id: row["record_id"]
                     .value::<String>()?
                     .expect("record_id is null"),
-                inputs: ipt,
+                inputs: ipt.trim().to_owned(),
                 token_estimate,
             });
         }