🎉 feat: Code Interpreter API and Agents Release

.env.example

@@ -177,10 +177,10 @@ OPENAI_API_KEY=user_provided
 DEBUG_OPENAI=false
 
 # TITLE_CONVO=false
-# OPENAI_TITLE_MODEL=gpt-3.5-turbo
+# OPENAI_TITLE_MODEL=gpt-4o-mini
 
 # OPENAI_SUMMARIZE=true
-# OPENAI_SUMMARY_MODEL=gpt-3.5-turbo
+# OPENAI_SUMMARY_MODEL=gpt-4o-mini
 
 # OPENAI_FORCE_PROMPT=true
 

api/app/clients/BaseClient.js

@@ -50,6 +50,8 @@ class BaseClient {
     /** The key for the usage object's output tokens
      * @type {string} */
     this.outputTokensKey = 'completion_tokens';
+    /** @type {Set<string>} */
+    this.savedMessageIds = new Set();
   }
 
   setOptions() {
@@ -84,7 +86,7 @@ class BaseClient {
       return this.options.agent.id;
     }
 
-    return this.modelOptions.model;
+    return this.modelOptions?.model ?? this.model;
   }
 
   /**
@@ -508,7 +510,7 @@ class BaseClient {
           conversationId,
           parentMessageId: userMessage.messageId,
           isCreatedByUser: false,
-          model: this.modelOptions.model,
+          model: this.modelOptions?.model ?? this.model,
           sender: this.sender,
           text: generation,
         };
@@ -545,6 +547,7 @@ class BaseClient {
 
     if (!isEdited && !this.skipSaveUserMessage) {
       this.userMessagePromise = this.saveMessageToDatabase(userMessage, saveOptions, user);
+      this.savedMessageIds.add(userMessage.messageId);
       if (typeof opts?.getReqData === 'function') {
         opts.getReqData({
           userMessagePromise: this.userMessagePromise,
@@ -563,8 +566,8 @@ class BaseClient {
           user: this.user,
           tokenType: 'prompt',
           amount: promptTokens,
-          model: this.modelOptions.model,
           endpoint: this.options.endpoint,
+          model: this.modelOptions?.model ?? this.model,
           endpointTokenConfig: this.options.endpointTokenConfig,
         },
       });
@@ -574,6 +577,7 @@ class BaseClient {
     const completion = await this.sendCompletion(payload, opts);
     this.abortController.requestCompleted = true;
 
+    /** @type {TMessage} */
     const responseMessage = {
       messageId: responseMessageId,
       conversationId,
@@ -635,7 +639,16 @@ class BaseClient {
       responseMessage.attachments = (await Promise.all(this.artifactPromises)).filter((a) => a);
     }
 
+    if (this.options.attachments) {
+      try {
+        saveOptions.files = this.options.attachments.map((attachments) => attachments.file_id);
+      } catch (error) {
+        logger.error('[BaseClient] Error mapping attachments for conversation', error);
+      }
+    }
+
     this.responsePromise = this.saveMessageToDatabase(responseMessage, saveOptions, user);
+    this.savedMessageIds.add(responseMessage.messageId);
     const messageCache = getLogStores(CacheKeys.MESSAGES);
     messageCache.set(
       responseMessageId,
@@ -902,8 +915,9 @@ class BaseClient {
     // Note: gpt-3.5-turbo and gpt-4 may update over time. Use default for these as well as for unknown models
     let tokensPerMessage = 3;
     let tokensPerName = 1;
+    const model = this.modelOptions?.model ?? this.model;
 
-    if (this.modelOptions.model === 'gpt-3.5-turbo-0301') {
+    if (model === 'gpt-3.5-turbo-0301') {
       tokensPerMessage = 4;
       tokensPerName = -1;
     }
@@ -961,6 +975,15 @@ class BaseClient {
       return _messages;
     }
 
+    const seen = new Set();
+    const attachmentsProcessed =
+      this.options.attachments && !(this.options.attachments instanceof Promise);
+    if (attachmentsProcessed) {
+      for (const attachment of this.options.attachments) {
+        seen.add(attachment.file_id);
+      }
+    }
+
     /**
      *
      * @param {TMessage} message
@@ -971,7 +994,19 @@ class BaseClient {
         this.message_file_map = {};
       }
 
-      const fileIds = message.files.map((file) => file.file_id);
+      const fileIds = [];
+      for (const file of message.files) {
+        if (seen.has(file.file_id)) {
+          continue;
+        }
+        fileIds.push(file.file_id);
+        seen.add(file.file_id);
+      }
+
+      if (fileIds.length === 0) {
+        return message;
+      }
+
       const files = await getFiles({
         file_id: { $in: fileIds },
       });

api/app/clients/OpenAIClient.js

@@ -688,7 +688,7 @@ class OpenAIClient extends BaseClient {
   }
 
   initializeLLM({
-    model = 'gpt-3.5-turbo',
+    model = 'gpt-4o-mini',
     modelName,
     temperature = 0.2,
     presence_penalty = 0,
@@ -793,7 +793,7 @@ class OpenAIClient extends BaseClient {
 
     const { OPENAI_TITLE_MODEL } = process.env ?? {};
 
-    let model = this.options.titleModel ?? OPENAI_TITLE_MODEL ?? 'gpt-3.5-turbo';
+    let model = this.options.titleModel ?? OPENAI_TITLE_MODEL ?? 'gpt-4o-mini';
     if (model === Constants.CURRENT_MODEL) {
       model = this.modelOptions.model;
     }
@@ -982,7 +982,7 @@ ${convo}
     let prompt;
 
     // TODO: remove the gpt fallback and make it specific to endpoint
-    const { OPENAI_SUMMARY_MODEL = 'gpt-3.5-turbo' } = process.env ?? {};
+    const { OPENAI_SUMMARY_MODEL = 'gpt-4o-mini' } = process.env ?? {};
     let model = this.options.summaryModel ?? OPENAI_SUMMARY_MODEL;
     if (model === Constants.CURRENT_MODEL) {
       model = this.modelOptions.model;

api/app/clients/PluginsClient.js

@@ -105,7 +105,7 @@ class PluginsClient extends OpenAIClient {
       chatHistory: new ChatMessageHistory(pastMessages),
     });
 
-    this.tools = await loadTools({
+    const { loadedTools } = await loadTools({
       user,
       model,
       tools: this.options.tools,
@@ -119,12 +119,15 @@ class PluginsClient extends OpenAIClient {
         processFileURL,
         message,
       },
+      useSpecs: true,
     });
 
-    if (this.tools.length === 0) {
+    if (loadedTools.length === 0) {
       return;
     }
 
+    this.tools = loadedTools;
+
     logger.debug('[PluginsClient] Requested Tools', this.options.tools);
     logger.debug(
       '[PluginsClient] Loaded Tools',

api/app/clients/llm/createLLM.js

@@ -17,7 +17,7 @@ const { isEnabled } = require('~/server/utils');
  *
  * @example
  * const llm = createLLM({
- *   modelOptions: { modelName: 'gpt-3.5-turbo', temperature: 0.2 },
+ *   modelOptions: { modelName: 'gpt-4o-mini', temperature: 0.2 },
  *   configOptions: { basePath: 'https://example.api/path' },
  *   callbacks: { onMessage: handleMessage },
  *   openAIApiKey: 'your-api-key'

api/app/clients/memory/summaryBuffer.demo.js

@@ -3,7 +3,7 @@ const { ChatOpenAI } = require('@langchain/openai');
 const { getBufferString, ConversationSummaryBufferMemory } = require('langchain/memory');
 
 const chatPromptMemory = new ConversationSummaryBufferMemory({
-  llm: new ChatOpenAI({ modelName: 'gpt-3.5-turbo', temperature: 0 }),
+  llm: new ChatOpenAI({ modelName: 'gpt-4o-mini', temperature: 0 }),
   maxTokenLimit: 10,
   returnMessages: true,
 });

api/app/clients/prompts/formatMessages.js

@@ -204,7 +204,7 @@ const formatAgentMessages = (payload) => {
           new ToolMessage({
             tool_call_id: tool_call.id,
             name: tool_call.name,
-            content: output,
+            content: output || '',
           }),
         );
       } else {

api/app/clients/specs/BaseClient.test.js

@@ -61,7 +61,7 @@ describe('BaseClient', () => {
   const options = {
     // debug: true,
     modelOptions: {
-      model: 'gpt-3.5-turbo',
+      model: 'gpt-4o-mini',
       temperature: 0,
     },
   };

api/app/clients/specs/OpenAIClient.test.js

@@ -221,7 +221,7 @@ describe('OpenAIClient', () => {
 
     it('should set isChatCompletion based on useOpenRouter, reverseProxyUrl, or model', () => {
       client.setOptions({ reverseProxyUrl: null });
-      // true by default since default model will be gpt-3.5-turbo
+      // true by default since default model will be gpt-4o-mini
       expect(client.isChatCompletion).toBe(true);
       client.isChatCompletion = undefined;
 
@@ -230,7 +230,7 @@ describe('OpenAIClient', () => {
       expect(client.isChatCompletion).toBe(false);
       client.isChatCompletion = undefined;
 
-      client.setOptions({ modelOptions: { model: 'gpt-3.5-turbo' }, reverseProxyUrl: null });
+      client.setOptions({ modelOptions: { model: 'gpt-4o-mini' }, reverseProxyUrl: null });
       expect(client.isChatCompletion).toBe(true);
     });
 

api/app/clients/tools/structured/DALLE3.js

@@ -19,6 +19,8 @@ class DALLE3 extends Tool {
 
     this.userId = fields.userId;
     this.fileStrategy = fields.fileStrategy;
+    /** @type {boolean} */
+    this.isAgent = fields.isAgent;
     if (fields.processFileURL) {
       /** @type {processFileURL} Necessary for output to contain all image metadata. */
       this.processFileURL = fields.processFileURL.bind(this);
@@ -108,6 +110,19 @@ class DALLE3 extends Tool {
     return `![generated image](${imageUrl})`;
   }
 
+  returnValue(value) {
+    if (this.isAgent === true && typeof value === 'string') {
+      return [value, {}];
+    } else if (this.isAgent === true && typeof value === 'object') {
+      return [
+        'DALL-E displayed an image. All generated images are already plainly visible, so don\'t repeat the descriptions in detail. Do not list download links as they are available in the UI already. The user may download the images by clicking on them, but do not mention anything about downloading to the user.',
+        value,
+      ];
+    }
+
+    return value;
+  }
+
   async _call(data) {
     const { prompt, quality = 'standard', size = '1024x1024', style = 'vivid' } = data;
     if (!prompt) {
@@ -126,18 +141,23 @@ class DALLE3 extends Tool {
       });
     } catch (error) {
       logger.error('[DALL-E-3] Problem generating the image:', error);
-      return `Something went wrong when trying to generate the image. The DALL-E API may be unavailable:
-Error Message: ${error.message}`;
+      return this
+        .returnValue(`Something went wrong when trying to generate the image. The DALL-E API may be unavailable:
+Error Message: ${error.message}`);
     }
 
     if (!resp) {
-      return 'Something went wrong when trying to generate the image. The DALL-E API may be unavailable';
+      return this.returnValue(
+        'Something went wrong when trying to generate the image. The DALL-E API may be unavailable',
+      );
     }
 
     const theImageUrl = resp.data[0].url;
 
     if (!theImageUrl) {
-      return 'No image URL returned from OpenAI API. There may be a problem with the API or your configuration.';
+      return this.returnValue(
+        'No image URL returned from OpenAI API. There may be a problem with the API or your configuration.',
+      );
     }
 
     const imageBasename = getImageBasename(theImageUrl);
@@ -157,11 +177,11 @@ Error Message: ${error.message}`;
 
     try {
       const result = await this.processFileURL({
-        fileStrategy: this.fileStrategy,
-        userId: this.userId,
         URL: theImageUrl,
-        fileName: imageName,
         basePath: 'images',
+        userId: this.userId,
+        fileName: imageName,
+        fileStrategy: this.fileStrategy,
         context: FileContext.image_generation,
       });
 
@@ -175,7 +195,7 @@ Error Message: ${error.message}`;
       this.result = `Failed to save the image locally. ${error.message}`;
     }
 
-    return this.result;
+    return this.returnValue(this.result);
   }
 }
 

api/app/clients/tools/util/createFileSearchTool.js → api/app/clients/tools/util/fileSearch.js

@@ -10,20 +10,50 @@ const { logger } = require('~/config');
  * @param {Object} options
  * @param {ServerRequest} options.req
  * @param {Agent['tool_resources']} options.tool_resources
- * @returns
+ * @returns {Promise<{
+ *   files: Array<{ file_id: string; filename: string }>,
+ *   toolContext: string
+ * }>}
  */
-const createFileSearchTool = async (options) => {
-  const { req, tool_resources } = options;
+const primeFiles = async (options) => {
+  const { tool_resources } = options;
   const file_ids = tool_resources?.[EToolResources.file_search]?.file_ids ?? [];
-  const files = (await getFiles({ file_id: { $in: file_ids } })).map((file) => ({
-    file_id: file.file_id,
-    filename: file.filename,
-  }));
+  const agentResourceIds = new Set(file_ids);
+  const resourceFiles = tool_resources?.[EToolResources.file_search]?.files ?? [];
+  const dbFiles = ((await getFiles({ file_id: { $in: file_ids } })) ?? []).concat(resourceFiles);
+
+  let toolContext = `- Note: Semantic search is available through the ${Tools.file_search} tool but no files are currently loaded. Request the user to upload documents to search through.`;
+
+  const files = [];
+  for (let i = 0; i < dbFiles.length; i++) {
+    const file = dbFiles[i];
+    if (!file) {
+      continue;
+    }
+    if (i === 0) {
+      toolContext = `- Note: Use the ${Tools.file_search} tool to find relevant information within:`;
+    }
+    toolContext += `\n\t- ${file.filename}${
+      agentResourceIds.has(file.file_id) ? '' : ' (just attached by user)'
+    }`;
+    files.push({
+      file_id: file.file_id,
+      filename: file.filename,
+    });
+  }
 
-  const fileList = files.map((file) => `- ${file.filename}`).join('\n');
-  const toolDescription = `Performs a semantic search based on a natural language query across the following files:\n${fileList}`;
+  return { files, toolContext };
+};
 
-  const FileSearch = tool(
+/**
+ *
+ * @param {Object} options
+ * @param {ServerRequest} options.req
+ * @param {Array<{ file_id: string; filename: string }>} options.files
+ * @returns
+ */
+const createFileSearchTool = async ({ req, files }) => {
+  return tool(
     async ({ query }) => {
       if (files.length === 0) {
         return 'No files to search. Instruct the user to add files for the search.';
@@ -87,7 +117,7 @@ const createFileSearchTool = async (options) => {
     },
     {
       name: Tools.file_search,
-      description: toolDescription,
+      description: `Performs semantic search across attached "${Tools.file_search}" documents using natural language queries. This tool analyzes the content of uploaded files to find relevant information, quotes, and passages that best match your query. Use this to extract specific information or find relevant sections within the available documents.`,
       schema: z.object({
         query: z
           .string()
@@ -97,8 +127,6 @@ const createFileSearchTool = async (options) => {
       }),
     },
   );
-
-  return FileSearch;
 };
 
-module.exports = createFileSearchTool;
+module.exports = { createFileSearchTool, primeFiles };