Enhance PerplexityService with new interfaces and streaming chat completion method

- Added PerplexityToolFunction, PerplexityTool, and PerplexityResponseFormat interfaces to support enhanced functionality.
- Introduced tools and response_format options in PerplexityRequest for improved API interactions.
- Implemented createStreamingChatCompletion method for querying the Perplexity AI API with streaming responses, including optional parameters for flexibility.
- Updated error handling in the new method to improve logging and error reporting.

Author: adamrefaey

backend/src/services/perplexity.service.ts

@@ -8,6 +8,21 @@ export interface PerplexityMessage {
   content: string;
 }
 
+export interface PerplexityToolFunction {
+  name: string;
+  description?: string;
+  parameters: Record<string, any>;
+}
+
+export interface PerplexityTool {
+  type: 'function';
+  function: PerplexityToolFunction;
+}
+
+export interface PerplexityResponseFormat {
+  type: 'text' | 'json_object';
+}
+
 export interface PerplexityRequest {
   model: string;
   messages: PerplexityMessage[];
@@ -18,6 +33,17 @@ export interface PerplexityRequest {
   presence_penalty?: number;
   frequency_penalty?: number;
   stream?: boolean;
+  tools?: PerplexityTool[];
+  response_format?: PerplexityResponseFormat;
+}
+
+export interface PerplexityToolCall {
+  id: string;
+  type: string;
+  function: {
+    name: string;
+    arguments: string;
+  };
 }
 
 export interface PerplexityResponse {
@@ -32,6 +58,7 @@ export interface PerplexityResponse {
     completion_tokens: number;
     total_tokens: number;
   };
+  tool_calls?: PerplexityToolCall[];
 }
 
 /**
@@ -104,6 +131,12 @@ export class PerplexityService {
       model?: string;
       maxTokens?: number;
       temperature?: number;
+      topP?: number;
+      topK?: number;
+      presencePenalty?: number;
+      frequencyPenalty?: number;
+      tools?: PerplexityTool[];
+      responseFormat?: PerplexityResponseFormat;
     },
   ): Promise<PerplexityResponse> {
     try {
@@ -116,6 +149,16 @@ export class PerplexityService {
         temperature: options?.temperature || 0.7,
       };
 
+      // Add optional parameters if provided
+      if (options?.topP !== undefined) request.top_p = options.topP;
+      if (options?.topK !== undefined) request.top_k = options.topK;
+      if (options?.presencePenalty !== undefined)
+        request.presence_penalty = options.presencePenalty;
+      if (options?.frequencyPenalty !== undefined)
+        request.frequency_penalty = options.frequencyPenalty;
+      if (options?.tools) request.tools = options.tools;
+      if (options?.responseFormat) request.response_format = options.responseFormat;
+
       const response = await axios.post<PerplexityResponse>(
         `${this.baseUrl}/chat/completions`,
         request,
@@ -140,6 +183,68 @@ export class PerplexityService {
     }
   }
 
+  /**
+   * Queries the Perplexity AI API with streaming responses
+   * @returns A readable stream of the response
+   */
+  async createStreamingChatCompletion(
+    messages: PerplexityMessage[],
+    options?: {
+      model?: string;
+      maxTokens?: number;
+      temperature?: number;
+      topP?: number;
+      topK?: number;
+      presencePenalty?: number;
+      frequencyPenalty?: number;
+      tools?: PerplexityTool[];
+      responseFormat?: PerplexityResponseFormat;
+    },
+  ): Promise<ReadableStream> {
+    try {
+      const apiKey = await this.getApiKey();
+
+      const request: PerplexityRequest = {
+        model: options?.model || this.defaultModel,
+        messages,
+        max_tokens: options?.maxTokens || this.defaultMaxTokens,
+        temperature: options?.temperature || 0.7,
+        stream: true,
+      };
+
+      // Add optional parameters if provided
+      if (options?.topP !== undefined) request.top_p = options.topP;
+      if (options?.topK !== undefined) request.top_k = options.topK;
+      if (options?.presencePenalty !== undefined)
+        request.presence_penalty = options.presencePenalty;
+      if (options?.frequencyPenalty !== undefined)
+        request.frequency_penalty = options.frequencyPenalty;
+      if (options?.tools) request.tools = options.tools;
+      if (options?.responseFormat) request.response_format = options.responseFormat;
+
+      const response = await axios.post(`${this.baseUrl}/chat/completions`, request, {
+        headers: {
+          'Content-Type': 'application/json',
+          Authorization: `Bearer ${apiKey}`,
+        },
+        responseType: 'stream',
+      });
+
+      return response.data;
+    } catch (error: unknown) {
+      if (axios.isAxiosError(error)) {
+        this.logger.error(
+          `Perplexity API streaming error: ${error.response?.status} - ${error.message}`,
+        );
+        throw new Error(`Perplexity API streaming error: ${error.message}`);
+      }
+
+      const errorMessage = error instanceof Error ? error.message : 'Unknown error';
+      this.logger.error(`Failed to create streaming chat completion: ${errorMessage}`);
+      throw new Error('Failed to create streaming chat completion');
+    }
+  }
+
   /**
    * Generates a simplified explanation of medical text
    *
@@ -197,6 +302,7 @@ export class PerplexityService {
       const response = await this.createChatCompletion(messages, {
         temperature: 0.3, // Lower temperature for more accurate/factual responses
         maxTokens: 4000, // Ensure there's enough space for the full corrected analysis
+        responseFormat: { type: 'json_object' }, // Use JSON mode for reliable JSON response
       });
 
       // Parse the response to get the corrected analysis