test

app/main.py

@@ -9,6 +9,7 @@ from fastapi.middleware import Middleware
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import StreamingResponse
 from .rag import ChatPDF
+import pdfplumber
 
 middleware = [
     Middleware(
@@ -64,6 +65,12 @@ def upload(data: bytes = Depends(parse_body)):
             path = f"{files_dir}/file.pdf"
             with open(path, "wb") as f:
                 f.write(data)
+            # with open(path, "wb") as f:
+            pdf = pdfplumber.open(path)
+            page = pdf.pages[0]
+            text = page.extract_text()
+            print(text)
+            pdf.close()
             session_assistant.ingest(files_dir)
             pathlib.Path(path).unlink()
         except Exception as e:

requirements.txt

@@ -6,4 +6,5 @@ llama-index-llms-llama-cpp
 llama-index-embeddings-fastembed
 qdrant-client
 unstructured
-fastembed==0.2.7
+fastembed==0.2.7
+pdfplumber