feat: 🧩 enhance PDF parser with image support

microsoft · Nov 17, 2024 · ddc245c · ddc245c
1 parent 492d0fe
commit ddc245c
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 2 deletions.
diff --git a/packages/core/src/parsers.test.ts b/packages/core/src/parsers.test.ts
@@ -47,7 +47,8 @@ describe("parsers", () => {
     })
 
     test("PDF", async () => {
-        const result = await parsers.PDF({ filename: "src/rag/loremipsum.pdf" })
+        const result = await parsers.PDF({ filename: "./src/rag/loremipsum.pdf" })
+        console.log(result)
         assert(result.file.content.includes("Lorem"))
     })
 

diff --git a/packages/core/src/types/prompt_template.d.ts b/packages/core/src/types/prompt_template.d.ts
@@ -1326,7 +1326,9 @@ interface Parsers {
     PDF(
         content: string | WorkspaceFile,
         options?: ParsePDFOptions
-    ): Promise<{ file: WorkspaceFile; pages: string[] } | undefined>
+    ): Promise<
+        { file: WorkspaceFile; pages: string[]; images?: Buffer[] } | undefined
+    >
 
     /**
      * Parses a .docx file