Adding the ability to find the chunks of a document given its name (#42)

* DocumentName in search and sourcereference

* Updated SDKs README

---------

Co-authored-by: Your Name <[email protected]>

protos/chunks.proto

@@ -25,6 +25,8 @@ message SourceReference {
     string document_version = 5;
     // Document path in the source system e.g. "My Drive/document.txt", "slack-channel-name"
     optional string document_path = 6;
+    // Document name in the source system e.g. "document.txt"
+    optional string document_name = 7;
 }
 
 message ChunkReference {

protos/search.proto

@@ -10,6 +10,8 @@ import "chunks.proto";
 service Search {
     // Query the index for relevant chunks
     rpc QueryChunks(QueryRequest) returns (QueryResponse);
+    // Query the index for all chunks of a specific document
+    rpc QueryChunksByDocumentName(QueryByDocumentNameRequest) returns (QueryByDocumentNameResponse);
     // Get chunks by URL
     rpc GetChunksByUrl(GetChunksByUrlRequest) returns (GetChunksByUrlResponse);
 }
@@ -19,6 +21,11 @@ message Query {
     string semantic_query = 1;
 }
 
+message DocumentNameQuery {
+    // Document name to search for
+    string document_name = 1;
+}
+
 message TimeSpan {
     optional google.protobuf.Timestamp after = 1;
     optional google.protobuf.Timestamp before = 2;
@@ -68,3 +75,19 @@ message GetChunksByUrlResponse {
     // List of chunks
     repeated Chunk chunks = 3;
 }
+
+message QueryByDocumentNameRequest {
+    // The query to execute
+    DocumentNameQuery query = 2;
+    // Filters to apply to query
+    optional Filters filters = 3;
+}
+
+message QueryByDocumentNameResponse {
+    // Query was successful
+    bool success = 1;
+    // Error message if query failed
+    optional google.protobuf.Struct error = 2;
+    // List of relevant chunks
+    repeated Chunk chunks = 3;
+}

sdks/node/README.md

@@ -51,15 +51,29 @@ const response = await client.exchangeTokens("OAUTH2-AUTH-CODE");
 
 ### SearchClient
 
-With the Redactive access_token, User can search documents with Redactive Search service.
+With the Redactive access_token, you can perform three types of searches using the Redactive Search service:
+
+1. **Semantic Query Search**: Retrieve relevant chunks of information that are semantically related to a user query.
+2. **URL-based Search**: Obtain all the chunks from a document by specifying its URL.
+3. **Document Name Search**: Query for all the chunks from a document based on the name of the document.
 
 ```javascript
 import { SearchClient } from "@redactive/redactive";
 
 const client = new SearchClient();
 const accessToken = "REDACTIVE-ACCESS-TOKEN";
+
+// Semantic Search: retrieve text extracts (chunks) from various documents pertaining to the user query
 const semanticQuery = "Tell me about AI";
 await client.queryChunks({ accessToken, semanticQuery });
+
+// URL-based Search: retrieve all chunks of the document at that URL
+const url = "https://example.com/document";
+await client.getChunksByUrl({ accessToken, url });
+
+// Document Name Search : retrieve all chunks of a document identified by its name
+const documentName = "AI Research Paper";
+await client.queryChunksByDocumentName({ accessToken, documentName });
 ```
 
 ## Development