A collaborative search engine is used for a group of users who want to search information together for various group activities. This will be time saving as the users can split the work between them. Summarization is the process of condensing a document into a shorter version which will contain the important details about the document. This will be useful to quickly get the main ideas without having to go through the entire document. Our main aim is to combine collaborative search with document summarization so that it will be helpful when users in a group want to quickly read the summary of the documents whenever required. In the collaborative search, the results will be re-ranked based on the user's interaction with the system, so that feedback driven ranking of results is attained and the users in a session will be able to view pages that were even ranked by their co-mates. This re-raking process is done by obtaining the user's interest on a particular page using decision logic and updating it in the priority queue. User's meta-data like page size, click-through rate, time spent and scrolling speed of the document will be calculated and these will be used as parameters for the decision logic to find the interest level of the user. Extractive summarization is implemented with the concept of Maximum Independent Set. The raw text document is first converted into a graph having its sentences as nodes and the edge weight is the similar instances between sentences. Then graph MIS is identified and removed after which the top-n sentences are fetched upon its eigenvector centrality value and the summary is generated.