web: fetch pdf text by pages

2026-06-20 21:22:55 +09:00
parent e752a7206a
commit b1af95ad20
4 changed files with 552 additions and 23 deletions
@@ -16,6 +16,7 @@ llm-worker = { workspace = true }
 manifest = { workspace = true }
 secrets = { workspace = true }
 markup5ever_rcdom = "0.2"
+pdf-extract = "0.10.0"
 reqwest = { version = "0.13", default-features = false, features = ["json", "native-tls"] }
 schemars = { workspace = true }
 serde = { workspace = true, features = ["derive"] }