There is a requirement for document recommendation frameworks focusing on certain domains linked to medical sciences and biosciences like biomedical document recommendation in the era of the Web 3.0. This paper proposes a biomedical document recommendation strategy that realizes informative term generation using the encompassment of extraction of terms and categories and the TF-IDF. The framework also generates an ontology from the informative terms harvested from which features are selected to classify the dataset using a random forest classifier. The model also uses very strong knowledge bases that are highly specific to the domain like QIAGEN. It also uses WikiData which is generic but has a full cover of world knowledge to bridge the knowledge present in the datasets and the existing structure web. Metadata generation also increases the quantity of additional knowledge that is encompassed in the model. BioBERT is a strategic large language model that focuses on biosciences and biomedicine as its domain is used to classify the metadata to make it more permeable into the model. Semantic similarity is computed using NPMI, web overlap, SimRank, and Ricklefs and Lau index at different stages in the pipeline to facilitate quantitative reasoning through semantic relatedness computation. The salient semantic analysis also accelerates the overall semantic association into the proposed framework. This framework can demonstrate a precision of 96.56%, recall of 96.93%, and an FDR of 0.04.