Pancreatic ductal adenocarcinoma (PDAC) is a highly mortal cancer whose only potentially curative treatment is surgical resection. Intraoperative assessment of its surgical margins is vital for patient survival. Frozen-section biopsy is routinely performed for this purpose. However, its high dependence on pathologists' experience frequently poses diagnostic discrepancies. The essential invasiveness of PDAC also causes sampling errors. This study developed an intelligent molecular cytology approach with improved diagnostic objectivity and broader sampling coverage. Our method, Multi-Instance Cytology with Learned Raman Embedding (MICLEAR), is characterized by compositional information provided by label-free Raman imaging. First, 4085 cells were brushed off from the pancreases of 41 patients and imaged using stimulated Raman scattering microscopy. Then, a contrastive learning-based cell embedding model was developed to compress each cell's morphological and compositional information into a compact cell vector. Finally, a multi-instance learning-based diagnosis model using cell vectors was employed to predict the likelihood of a patient's margin being positive. MICLEAR achieved 80% sensitivity, 94.1% specificity, and an AUC of 0.86 on 27 patients for validation, comprising 10 with positive margins and 17 with negative ones, within approximately 8 minutes per patient. It may hold promises for more efficient and accurate intraoperative assessment of PDAC surgical margins.