feature: add route to get message by id

clients/ts-sdk/openapi.json

@@ -12,7 +12,7 @@
       "name": "BSL",
       "url": "https://github.com/devflowinc/trieve/blob/main/LICENSE.txt"
     },
-    "version": "0.12.0"
+    "version": "0.12.1"
   },
   "servers": [
     {
@@ -1426,7 +1426,7 @@
           "Chunk"
         ],
         "summary": "Split HTML Content into Chunks",
-        "description": "This endpoint receives a single html string and splits it into chunks based on the headings and\nbody content. The headings are split based on headding html tags. chunk_html has a maximum size\nof 256Kb.",
+        "description": "This endpoint receives a single html string and splits it into chunks based on the headings and\nbody content. The headings are split based on heading html tags. chunk_html has a maximum size\nof 256Kb.",
         "operationId": "split_html_content",
         "requestBody": {
           "description": "JSON request payload to perform RAG on some chunks (chunks)",
@@ -4648,7 +4648,7 @@
         "security": [
           {
             "ApiKey": [
-              "readonly"
+              "admin"
             ]
           }
         ]
@@ -4710,7 +4710,7 @@
         "security": [
           {
             "ApiKey": [
-              "readonly"
+              "admin"
             ]
           }
         ]
@@ -4780,7 +4780,7 @@
         "security": [
           {
             "ApiKey": [
-              "readonly"
+              "admin"
             ]
           }
         ]
@@ -4849,7 +4849,68 @@
         "security": [
           {
             "ApiKey": [
-              "readonly"
+              "admin"
+            ]
+          }
+        ]
+      }
+    },
+    "/api/message/{message_id}": {
+      "get": {
+        "tags": [
+          "Message"
+        ],
+        "summary": "Get a message by its ID",
+        "description": "Quickly get the full object for a given message. From the message, you can get the topic and all messages which exist on that topic.",
+        "operationId": "get_message_by_id",
+        "parameters": [
+          {
+            "name": "TR-Dataset",
+            "in": "header",
+            "description": "The dataset id or tracking_id to use for the request. We assume you intend to use an id if the value is a valid uuid.",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "format": "uuid"
+            }
+          },
+          {
+            "name": "message_id",
+            "in": "path",
+            "description": "The ID of the message to get.",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "format": "uuid"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Message with the given ID",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Message"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "Service error relating to getting the message",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponseBody"
+                }
+              }
+            }
+          }
+        },
+        "security": [
+          {
+            "ApiKey": [
+              "admin"
             ]
           }
         ]
@@ -4861,7 +4922,7 @@
           "Message"
         ],
         "summary": "Get all messages for a given topic",
-        "description": "Get all messages for a given topic. If the topic is a RAG topic then the response will include Chunks first on each message. The structure will look like `[chunks]||mesage`. See docs.trieve.ai for more information.",
+        "description": "If the topic is a RAG topic then the response will include Chunks first on each message. The structure will look like `[chunks]||mesage`. See docs.trieve.ai for more information.",
         "operationId": "get_all_topic_messages",
         "parameters": [
           {
@@ -13599,7 +13660,7 @@
           },
           "group_size": {
             "type": "integer",
-            "format": "int32",
+            "format": "int64",
             "description": "Group_size is the number of chunks to fetch for each group. The default is 3. If a group has less than group_size chunks, all chunks will be returned. If this is set to a large number, we recommend setting slim_chunks to true to avoid returning the content and chunk_html of the chunks so as to lower the amount of time required for content download and serialization.",
             "nullable": true,
             "minimum": 0
@@ -13648,6 +13709,14 @@
             "description": "Set slim_chunks to true to avoid returning the content and chunk_html of the chunks. This is useful for when you want to reduce amount of data over the wire for latency improvement (typicall 10-50ms). Default is false.",
             "nullable": true
           },
+          "sort_options": {
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/SortOptions"
+              }
+            ],
+            "nullable": true
+          },
           "typo_options": {
             "allOf": [
               {
@@ -15489,6 +15558,11 @@
             "type": "string",
             "description": "Time stamp should be an ISO 8601 combined date and time without timezone. Time_stamp is used for time window filtering and recency-biasing search results. Will be passed down to the file's chunks.",
             "nullable": true
+          },
+          "use_pdf2md_ocr": {
+            "type": "boolean",
+            "description": "Parameter to use pdf2md_ocr. If true, the file will be converted to markdown using gpt-4o.\nDefault is false.",
+            "nullable": true
           }
         },
         "example": {
@@ -15512,7 +15586,8 @@
             "tag2"
           ],
           "target_splits_per_chunk": 20,
-          "time_stamp": "2021-01-01 00:00:00.000Z"
+          "time_stamp": "2021-01-01 00:00:00.000Z",
+          "use_pdf2md_ocr": false
         }
       },
       "UploadFileResult": {

clients/ts-sdk/package.json

@@ -6,7 +6,7 @@
   "files": [
     "dist"
   ],
-  "version": "0.0.30",
+  "version": "0.0.31",
   "license": "MIT",
   "scripts": {
     "lint": "eslint 'src/**/*.ts'",

clients/ts-sdk/src/functions/message/index.ts

@@ -7,6 +7,7 @@ import {
   CreateMessageReqPayload,
   EditMessageReqPayload,
   GetAllTopicMessagesData,
+  GetMessageByIdData,
   RegenerateMessageReqPayload,
 } from "../../fetch-client";
 import { TrieveSDK } from "../../sdk";
@@ -358,3 +359,31 @@ export async function getAllMessagesForTopic(
     signal
   );
 }
+
+/**
+ * Quickly get the full object for a given message. From the message, you can get the topic and all messages which exist on that topic.
+ * 
+ * Example:
+ * ```js
+ *const data = await trieve.getMessageById({
+  messageId: "3c90c3cc-1d76-27198-8888-8dd25736052a",
+});
+ * ```
+ */
+export async function getMessageById(
+  /** @hidden */
+  this: TrieveSDK,
+  data: Omit<GetMessageByIdData, "trDataset">,
+  signal?: AbortSignal
+) {
+  return await this.trieve.fetch(
+    "/api/message/{message_id}",
+    "get",
+    {
+      ...data,
+      datasetId: this.datasetId,
+    },
+    signal
+  );
+}
+

clients/ts-sdk/src/types.gen.ts

@@ -2396,6 +2396,7 @@ export type SearchOverGroupsReqPayload = {
      * Set slim_chunks to true to avoid returning the content and chunk_html of the chunks. This is useful for when you want to reduce amount of data over the wire for latency improvement (typicall 10-50ms). Default is false.
      */
     slim_chunks?: (boolean) | null;
+    sort_options?: ((SortOptions) | null);
     typo_options?: ((TypoOptions) | null);
     /**
      * If true, quoted and - prefixed words will be parsed from the queries and used as required and negated words respectively. Default is false.
@@ -3050,6 +3051,11 @@ export type UploadFileReqPayload = {
      * Time stamp should be an ISO 8601 combined date and time without timezone. Time_stamp is used for time window filtering and recency-biasing search results. Will be passed down to the file's chunks.
      */
     time_stamp?: (string) | null;
+    /**
+     * Parameter to use pdf2md_ocr. If true, the file will be converted to markdown using gpt-4o.
+     * Default is false.
+     */
+    use_pdf2md_ocr?: (boolean) | null;
 };
 
 export type UploadFileResult = {
@@ -4105,6 +4111,19 @@ export type RegenerateMessagePatchData = {
 
 export type RegenerateMessagePatchResponse = (string);
 
+export type GetMessageByIdData = {
+    /**
+     * The ID of the message to get.
+     */
+    messageId: string;
+    /**
+     * The dataset id or tracking_id to use for the request. We assume you intend to use an id if the value is a valid uuid.
+     */
+    trDataset: string;
+};
+
+export type GetMessageByIdResponse = (Message);
+
 export type GetAllTopicMessagesData = {
     /**
      * The ID of the topic to get messages for.
@@ -5533,6 +5552,21 @@ export type $OpenApiTs = {
             };
         };
     };
+    '/api/message/{message_id}': {
+        get: {
+            req: GetMessageByIdData;
+            res: {
+                /**
+                 * Message with the given ID
+                 */
+                200: Message;
+                /**
+                 * Service error relating to getting the message
+                 */
+                400: ErrorResponseBody;
+            };
+        };
+    };
     '/api/messages/{messages_topic_id}': {
         get: {
             req: GetAllTopicMessagesData;