diff --git a/server/utils/AiProviders/anthropic/index.js b/server/utils/AiProviders/anthropic/index.js
index 6a8ad3c4..d5ee1f9d 100644
--- a/server/utils/AiProviders/anthropic/index.js
+++ b/server/utils/AiProviders/anthropic/index.js
@@ -1,5 +1,4 @@
 const { v4 } = require("uuid");
-const { chatPrompt } = require("../../chats");
 const {
   writeResponseChunk,
   clientAbortedHandler,
@@ -33,7 +32,7 @@ class AnthropicLLM {
   }
 
   streamingEnabled() {
-    return "streamChat" in this && "streamGetChatCompletion" in this;
+    return "streamGetChatCompletion" in this;
   }
 
   promptWindowLimit() {
@@ -110,31 +109,6 @@ class AnthropicLLM {
     }
   }
 
-  async streamChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    if (!this.isValidChatCompletionModel(this.model))
-      throw new Error(
-        `Anthropic chat: ${this.model} is not valid for chat completion!`
-      );
-
-    const messages = await this.compressMessages(
-      {
-        systemPrompt: chatPrompt(workspace),
-        userPrompt: prompt,
-        chatHistory,
-      },
-      rawHistory
-    );
-
-    const streamRequest = await this.anthropic.messages.stream({
-      model: this.model,
-      max_tokens: 4096,
-      system: messages[0].content, // Strip out the system message
-      messages: messages.slice(1), // Pop off the system message
-      temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-    });
-    return streamRequest;
-  }
-
   async streamGetChatCompletion(messages = null, { temperature = 0.7 }) {
     if (!this.isValidChatCompletionModel(this.model))
       throw new Error(
diff --git a/server/utils/AiProviders/azureOpenAi/index.js b/server/utils/AiProviders/azureOpenAi/index.js
index 21fc5cd9..a2ab556d 100644
--- a/server/utils/AiProviders/azureOpenAi/index.js
+++ b/server/utils/AiProviders/azureOpenAi/index.js
@@ -1,5 +1,4 @@
 const { AzureOpenAiEmbedder } = require("../../EmbeddingEngines/azureOpenAi");
-const { chatPrompt } = require("../../chats");
 const {
   writeResponseChunk,
   clientAbortedHandler,
@@ -45,7 +44,7 @@ class AzureOpenAiLLM {
   }
 
   streamingEnabled() {
-    return "streamChat" in this && "streamGetChatCompletion" in this;
+    return "streamGetChatCompletion" in this;
   }
 
   // Sure the user selected a proper value for the token limit
@@ -82,66 +81,6 @@ class AzureOpenAiLLM {
     return { safe: true, reasons: [] };
   }
 
-  async sendChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    if (!this.model)
-      throw new Error(
-        "No OPEN_MODEL_PREF ENV defined. This must the name of a deployment on your Azure account for an LLM chat model like GPT-3.5."
-      );
-
-    const messages = await this.compressMessages(
-      {
-        systemPrompt: chatPrompt(workspace),
-        userPrompt: prompt,
-        chatHistory,
-      },
-      rawHistory
-    );
-    const textResponse = await this.openai
-      .getChatCompletions(this.model, messages, {
-        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-        n: 1,
-      })
-      .then((res) => {
-        if (!res.hasOwnProperty("choices"))
-          throw new Error("AzureOpenAI chat: No results!");
-        if (res.choices.length === 0)
-          throw new Error("AzureOpenAI chat: No results length!");
-        return res.choices[0].message.content;
-      })
-      .catch((error) => {
-        console.log(error);
-        throw new Error(
-          `AzureOpenAI::getChatCompletions failed with: ${error.message}`
-        );
-      });
-    return textResponse;
-  }
-
-  async streamChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    if (!this.model)
-      throw new Error(
-        "No OPEN_MODEL_PREF ENV defined. This must the name of a deployment on your Azure account for an LLM chat model like GPT-3.5."
-      );
-
-    const messages = await this.compressMessages(
-      {
-        systemPrompt: chatPrompt(workspace),
-        userPrompt: prompt,
-        chatHistory,
-      },
-      rawHistory
-    );
-    const stream = await this.openai.streamChatCompletions(
-      this.model,
-      messages,
-      {
-        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-        n: 1,
-      }
-    );
-    return stream;
-  }
-
   async getChatCompletion(messages = [], { temperature = 0.7 }) {
     if (!this.model)
       throw new Error(
diff --git a/server/utils/AiProviders/gemini/index.js b/server/utils/AiProviders/gemini/index.js
index 354c1899..b9eb26c3 100644
--- a/server/utils/AiProviders/gemini/index.js
+++ b/server/utils/AiProviders/gemini/index.js
@@ -1,4 +1,3 @@
-const { chatPrompt } = require("../../chats");
 const {
   writeResponseChunk,
   clientAbortedHandler,
@@ -48,7 +47,7 @@ class GeminiLLM {
   }
 
   streamingEnabled() {
-    return "streamChat" in this && "streamGetChatCompletion" in this;
+    return "streamGetChatCompletion" in this;
   }
 
   promptWindowLimit() {
@@ -118,32 +117,6 @@ class GeminiLLM {
     return allMessages;
   }
 
-  async sendChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    if (!this.isValidChatCompletionModel(this.model))
-      throw new Error(
-        `Gemini chat: ${this.model} is not valid for chat completion!`
-      );
-
-    const compressedHistory = await this.compressMessages(
-      {
-        systemPrompt: chatPrompt(workspace),
-        chatHistory,
-      },
-      rawHistory
-    );
-
-    const chatThread = this.gemini.startChat({
-      history: this.formatMessages(compressedHistory),
-    });
-    const result = await chatThread.sendMessage(prompt);
-    const response = result.response;
-    const responseText = response.text();
-
-    if (!responseText) throw new Error("Gemini: No response could be parsed.");
-
-    return responseText;
-  }
-
   async getChatCompletion(messages = [], _opts = {}) {
     if (!this.isValidChatCompletionModel(this.model))
       throw new Error(
@@ -165,30 +138,6 @@ class GeminiLLM {
     return responseText;
   }
 
-  async streamChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    if (!this.isValidChatCompletionModel(this.model))
-      throw new Error(
-        `Gemini chat: ${this.model} is not valid for chat completion!`
-      );
-
-    const compressedHistory = await this.compressMessages(
-      {
-        systemPrompt: chatPrompt(workspace),
-        chatHistory,
-      },
-      rawHistory
-    );
-
-    const chatThread = this.gemini.startChat({
-      history: this.formatMessages(compressedHistory),
-    });
-    const responseStream = await chatThread.sendMessageStream(prompt);
-    if (!responseStream.stream)
-      throw new Error("Could not stream response stream from Gemini.");
-
-    return responseStream.stream;
-  }
-
   async streamGetChatCompletion(messages = [], _opts = {}) {
     if (!this.isValidChatCompletionModel(this.model))
       throw new Error(
diff --git a/server/utils/AiProviders/genericOpenAi/index.js b/server/utils/AiProviders/genericOpenAi/index.js
index cf293c3e..8c171b67 100644
--- a/server/utils/AiProviders/genericOpenAi/index.js
+++ b/server/utils/AiProviders/genericOpenAi/index.js
@@ -1,5 +1,4 @@
 const { NativeEmbedder } = require("../../EmbeddingEngines/native");
-const { chatPrompt } = require("../../chats");
 const {
   handleDefaultStreamResponseV2,
 } = require("../../helpers/chat/responses");
@@ -53,7 +52,7 @@ class GenericOpenAiLLM {
   }
 
   streamingEnabled() {
-    return "streamChat" in this && "streamGetChatCompletion" in this;
+    return "streamGetChatCompletion" in this;
   }
 
   // Ensure the user set a value for the token limit
@@ -89,55 +88,6 @@ class GenericOpenAiLLM {
     return { safe: true, reasons: [] };
   }
 
-  async sendChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    const textResponse = await this.openai.chat.completions
-      .create({
-        model: this.model,
-        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-        n: 1,
-        messages: await this.compressMessages(
-          {
-            systemPrompt: chatPrompt(workspace),
-            userPrompt: prompt,
-            chatHistory,
-          },
-          rawHistory
-        ),
-      })
-      .then((result) => {
-        if (!result.hasOwnProperty("choices"))
-          throw new Error("GenericOpenAI chat: No results!");
-        if (result.choices.length === 0)
-          throw new Error("GenericOpenAI chat: No results length!");
-        return result.choices[0].message.content;
-      })
-      .catch((error) => {
-        throw new Error(
-          `GenericOpenAI::createChatCompletion failed with: ${error.message}`
-        );
-      });
-
-    return textResponse;
-  }
-
-  async streamChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    const streamRequest = await this.openai.chat.completions.create({
-      model: this.model,
-      stream: true,
-      temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-      n: 1,
-      messages: await this.compressMessages(
-        {
-          systemPrompt: chatPrompt(workspace),
-          userPrompt: prompt,
-          chatHistory,
-        },
-        rawHistory
-      ),
-    });
-    return streamRequest;
-  }
-
   async getChatCompletion(messages = null, { temperature = 0.7 }) {
     const result = await this.openai.chat.completions
       .create({
diff --git a/server/utils/AiProviders/groq/index.js b/server/utils/AiProviders/groq/index.js
index add064af..01d92f00 100644
--- a/server/utils/AiProviders/groq/index.js
+++ b/server/utils/AiProviders/groq/index.js
@@ -1,5 +1,4 @@
 const { NativeEmbedder } = require("../../EmbeddingEngines/native");
-const { chatPrompt } = require("../../chats");
 const {
   handleDefaultStreamResponseV2,
 } = require("../../helpers/chat/responses");
@@ -38,7 +37,7 @@ class GroqLLM {
   }
 
   streamingEnabled() {
-    return "streamChat" in this && "streamGetChatCompletion" in this;
+    return "streamGetChatCompletion" in this;
   }
 
   promptWindowLimit() {
@@ -91,65 +90,6 @@ class GroqLLM {
     return { safe: true, reasons: [] };
   }
 
-  async sendChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    if (!(await this.isValidChatCompletionModel(this.model)))
-      throw new Error(
-        `Groq chat: ${this.model} is not valid for chat completion!`
-      );
-
-    const textResponse = await this.openai.chat.completions
-      .create({
-        model: this.model,
-        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-        n: 1,
-        messages: await this.compressMessages(
-          {
-            systemPrompt: chatPrompt(workspace),
-            userPrompt: prompt,
-            chatHistory,
-          },
-          rawHistory
-        ),
-      })
-      .then((result) => {
-        if (!result.hasOwnProperty("choices"))
-          throw new Error("GroqAI chat: No results!");
-        if (result.choices.length === 0)
-          throw new Error("GroqAI chat: No results length!");
-        return result.choices[0].message.content;
-      })
-      .catch((error) => {
-        throw new Error(
-          `GroqAI::createChatCompletion failed with: ${error.message}`
-        );
-      });
-
-    return textResponse;
-  }
-
-  async streamChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    if (!(await this.isValidChatCompletionModel(this.model)))
-      throw new Error(
-        `GroqAI:streamChat: ${this.model} is not valid for chat completion!`
-      );
-
-    const streamRequest = await this.openai.chat.completions.create({
-      model: this.model,
-      stream: true,
-      temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-      n: 1,
-      messages: await this.compressMessages(
-        {
-          systemPrompt: chatPrompt(workspace),
-          userPrompt: prompt,
-          chatHistory,
-        },
-        rawHistory
-      ),
-    });
-    return streamRequest;
-  }
-
   async getChatCompletion(messages = null, { temperature = 0.7 }) {
     if (!(await this.isValidChatCompletionModel(this.model)))
       throw new Error(
diff --git a/server/utils/AiProviders/huggingface/index.js b/server/utils/AiProviders/huggingface/index.js
index 22f9c2fd..6a79880c 100644
--- a/server/utils/AiProviders/huggingface/index.js
+++ b/server/utils/AiProviders/huggingface/index.js
@@ -1,6 +1,5 @@
 const { NativeEmbedder } = require("../../EmbeddingEngines/native");
 const { OpenAiEmbedder } = require("../../EmbeddingEngines/openAi");
-const { chatPrompt } = require("../../chats");
 const {
   handleDefaultStreamResponseV2,
 } = require("../../helpers/chat/responses");
@@ -48,7 +47,7 @@ class HuggingFaceLLM {
   }
 
   streamingEnabled() {
-    return "streamChat" in this && "streamGetChatCompletion" in this;
+    return "streamGetChatCompletion" in this;
   }
 
   promptWindowLimit() {
@@ -90,55 +89,6 @@ class HuggingFaceLLM {
     return { safe: true, reasons: [] };
   }
 
-  async sendChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    const textResponse = await this.openai.chat.completions
-      .create({
-        model: this.model,
-        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-        n: 1,
-        messages: await this.compressMessages(
-          {
-            systemPrompt: chatPrompt(workspace),
-            userPrompt: prompt,
-            chatHistory,
-          },
-          rawHistory
-        ),
-      })
-      .then((result) => {
-        if (!result.hasOwnProperty("choices"))
-          throw new Error("HuggingFace chat: No results!");
-        if (result.choices.length === 0)
-          throw new Error("HuggingFace chat: No results length!");
-        return result.choices[0].message.content;
-      })
-      .catch((error) => {
-        throw new Error(
-          `HuggingFace::createChatCompletion failed with: ${error.message}`
-        );
-      });
-
-    return textResponse;
-  }
-
-  async streamChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    const streamRequest = await this.openai.chat.completions.create({
-      model: this.model,
-      stream: true,
-      temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-      n: 1,
-      messages: await this.compressMessages(
-        {
-          systemPrompt: chatPrompt(workspace),
-          userPrompt: prompt,
-          chatHistory,
-        },
-        rawHistory
-      ),
-    });
-    return streamRequest;
-  }
-
   async getChatCompletion(messages = null, { temperature = 0.7 }) {
     const result = await this.openai.createChatCompletion({
       model: this.model,
diff --git a/server/utils/AiProviders/lmStudio/index.js b/server/utils/AiProviders/lmStudio/index.js
index 98cbbcaa..48f689fb 100644
--- a/server/utils/AiProviders/lmStudio/index.js
+++ b/server/utils/AiProviders/lmStudio/index.js
@@ -1,4 +1,3 @@
-const { chatPrompt } = require("../../chats");
 const {
   handleDefaultStreamResponseV2,
 } = require("../../helpers/chat/responses");
@@ -49,7 +48,7 @@ class LMStudioLLM {
   }
 
   streamingEnabled() {
-    return "streamChat" in this && "streamGetChatCompletion" in this;
+    return "streamGetChatCompletion" in this;
   }
 
   // Ensure the user set a value for the token limit
@@ -85,65 +84,6 @@ class LMStudioLLM {
     return { safe: true, reasons: [] };
   }
 
-  async sendChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    if (!this.model)
-      throw new Error(
-        `LMStudio chat: ${this.model} is not valid or defined for chat completion!`
-      );
-
-    const textResponse = await this.lmstudio.chat.completions
-      .create({
-        model: this.model,
-        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-        n: 1,
-        messages: await this.compressMessages(
-          {
-            systemPrompt: chatPrompt(workspace),
-            userPrompt: prompt,
-            chatHistory,
-          },
-          rawHistory
-        ),
-      })
-      .then((result) => {
-        if (!result.hasOwnProperty("choices"))
-          throw new Error("LMStudio chat: No results!");
-        if (result.choices.length === 0)
-          throw new Error("LMStudio chat: No results length!");
-        return result.choices[0].message.content;
-      })
-      .catch((error) => {
-        throw new Error(
-          `LMStudio::createChatCompletion failed with: ${error.message}`
-        );
-      });
-
-    return textResponse;
-  }
-
-  async streamChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    if (!this.model)
-      throw new Error(
-        `LMStudio chat: ${this.model} is not valid or defined for chat completion!`
-      );
-
-    const streamRequest = await this.lmstudio.chat.completions.create({
-      model: this.model,
-      temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-      n: 1,
-      stream: true,
-      messages: await this.compressMessages(
-        {
-          systemPrompt: chatPrompt(workspace),
-          userPrompt: prompt,
-          chatHistory,
-        },
-        rawHistory
-      ),
-    });
-    return streamRequest;
-  }
-
   async getChatCompletion(messages = null, { temperature = 0.7 }) {
     if (!this.model)
       throw new Error(
diff --git a/server/utils/AiProviders/localAi/index.js b/server/utils/AiProviders/localAi/index.js
index 4a8921af..50477528 100644
--- a/server/utils/AiProviders/localAi/index.js
+++ b/server/utils/AiProviders/localAi/index.js
@@ -1,4 +1,3 @@
-const { chatPrompt } = require("../../chats");
 const {
   handleDefaultStreamResponseV2,
 } = require("../../helpers/chat/responses");
@@ -41,7 +40,7 @@ class LocalAiLLM {
   }
 
   streamingEnabled() {
-    return "streamChat" in this && "streamGetChatCompletion" in this;
+    return "streamGetChatCompletion" in this;
   }
 
   // Ensure the user set a value for the token limit
@@ -75,65 +74,6 @@ class LocalAiLLM {
     return { safe: true, reasons: [] };
   }
 
-  async sendChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    if (!(await this.isValidChatCompletionModel(this.model)))
-      throw new Error(
-        `LocalAI chat: ${this.model} is not valid for chat completion!`
-      );
-
-    const textResponse = await this.openai.chat.completions
-      .create({
-        model: this.model,
-        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-        n: 1,
-        messages: await this.compressMessages(
-          {
-            systemPrompt: chatPrompt(workspace),
-            userPrompt: prompt,
-            chatHistory,
-          },
-          rawHistory
-        ),
-      })
-      .then((result) => {
-        if (!result.hasOwnProperty("choices"))
-          throw new Error("LocalAI chat: No results!");
-        if (result.choices.length === 0)
-          throw new Error("LocalAI chat: No results length!");
-        return result.choices[0].message.content;
-      })
-      .catch((error) => {
-        throw new Error(
-          `LocalAI::createChatCompletion failed with: ${error.message}`
-        );
-      });
-
-    return textResponse;
-  }
-
-  async streamChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    if (!(await this.isValidChatCompletionModel(this.model)))
-      throw new Error(
-        `LocalAI chat: ${this.model} is not valid for chat completion!`
-      );
-
-    const streamRequest = await this.openai.chat.completions.create({
-      model: this.model,
-      stream: true,
-      temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-      n: 1,
-      messages: await this.compressMessages(
-        {
-          systemPrompt: chatPrompt(workspace),
-          userPrompt: prompt,
-          chatHistory,
-        },
-        rawHistory
-      ),
-    });
-    return streamRequest;
-  }
-
   async getChatCompletion(messages = null, { temperature = 0.7 }) {
     if (!(await this.isValidChatCompletionModel(this.model)))
       throw new Error(
diff --git a/server/utils/AiProviders/mistral/index.js b/server/utils/AiProviders/mistral/index.js
index 7b60f3fe..8410d4cb 100644
--- a/server/utils/AiProviders/mistral/index.js
+++ b/server/utils/AiProviders/mistral/index.js
@@ -1,4 +1,3 @@
-const { chatPrompt } = require("../../chats");
 const {
   handleDefaultStreamResponseV2,
 } = require("../../helpers/chat/responses");
@@ -42,7 +41,7 @@ class MistralLLM {
   }
 
   streamingEnabled() {
-    return "streamChat" in this && "streamGetChatCompletion" in this;
+    return "streamGetChatCompletion" in this;
   }
 
   promptWindowLimit() {
@@ -70,64 +69,6 @@ class MistralLLM {
     return { safe: true, reasons: [] };
   }
 
-  async sendChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    if (!(await this.isValidChatCompletionModel(this.model)))
-      throw new Error(
-        `Mistral chat: ${this.model} is not valid for chat completion!`
-      );
-
-    const textResponse = await this.openai.chat.completions
-      .create({
-        model: this.model,
-        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-        messages: await this.compressMessages(
-          {
-            systemPrompt: chatPrompt(workspace),
-            userPrompt: prompt,
-            chatHistory,
-          },
-          rawHistory
-        ),
-      })
-      .then((result) => {
-        if (!result.hasOwnProperty("choices"))
-          throw new Error("Mistral chat: No results!");
-        if (result.choices.length === 0)
-          throw new Error("Mistral chat: No results length!");
-        return result.choices[0].message.content;
-      })
-      .catch((error) => {
-        throw new Error(
-          `Mistral::createChatCompletion failed with: ${error.message}`
-        );
-      });
-
-    return textResponse;
-  }
-
-  async streamChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    if (!(await this.isValidChatCompletionModel(this.model)))
-      throw new Error(
-        `Mistral chat: ${this.model} is not valid for chat completion!`
-      );
-
-    const streamRequest = await this.openai.chat.completions.create({
-      model: this.model,
-      stream: true,
-      temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-      messages: await this.compressMessages(
-        {
-          systemPrompt: chatPrompt(workspace),
-          userPrompt: prompt,
-          chatHistory,
-        },
-        rawHistory
-      ),
-    });
-
-    return streamRequest;
-  }
-
   async getChatCompletion(messages = null, { temperature = 0.7 }) {
     if (!(await this.isValidChatCompletionModel(this.model)))
       throw new Error(
diff --git a/server/utils/AiProviders/native/index.js b/server/utils/AiProviders/native/index.js
index 07d8918c..e13b68a2 100644
--- a/server/utils/AiProviders/native/index.js
+++ b/server/utils/AiProviders/native/index.js
@@ -1,7 +1,6 @@
 const fs = require("fs");
 const path = require("path");
 const { NativeEmbedder } = require("../../EmbeddingEngines/native");
-const { chatPrompt } = require("../../chats");
 const {
   writeResponseChunk,
   clientAbortedHandler,
@@ -94,7 +93,7 @@ class NativeLLM {
   }
 
   streamingEnabled() {
-    return "streamChat" in this && "streamGetChatCompletion" in this;
+    return "streamGetChatCompletion" in this;
   }
 
   // Ensure the user set a value for the token limit
@@ -123,45 +122,6 @@ class NativeLLM {
     return { safe: true, reasons: [] };
   }
 
-  async sendChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    try {
-      const messages = await this.compressMessages(
-        {
-          systemPrompt: chatPrompt(workspace),
-          userPrompt: prompt,
-          chatHistory,
-        },
-        rawHistory
-      );
-
-      const model = await this.#llamaClient({
-        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-      });
-      const response = await model.call(messages);
-      return response.content;
-    } catch (error) {
-      throw new Error(
-        `NativeLLM::createChatCompletion failed with: ${error.message}`
-      );
-    }
-  }
-
-  async streamChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    const model = await this.#llamaClient({
-      temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-    });
-    const messages = await this.compressMessages(
-      {
-        systemPrompt: chatPrompt(workspace),
-        userPrompt: prompt,
-        chatHistory,
-      },
-      rawHistory
-    );
-    const responseStream = await model.stream(messages);
-    return responseStream;
-  }
-
   async getChatCompletion(messages = null, { temperature = 0.7 }) {
     const model = await this.#llamaClient({ temperature });
     const response = await model.call(messages);
diff --git a/server/utils/AiProviders/ollama/index.js b/server/utils/AiProviders/ollama/index.js
index a1931525..73269d6d 100644
--- a/server/utils/AiProviders/ollama/index.js
+++ b/server/utils/AiProviders/ollama/index.js
@@ -1,4 +1,3 @@
-const { chatPrompt } = require("../../chats");
 const { StringOutputParser } = require("@langchain/core/output_parsers");
 const {
   writeResponseChunk,
@@ -74,7 +73,7 @@ class OllamaAILLM {
   }
 
   streamingEnabled() {
-    return "streamChat" in this && "streamGetChatCompletion" in this;
+    return "streamGetChatCompletion" in this;
   }
 
   // Ensure the user set a value for the token limit
@@ -108,53 +107,6 @@ class OllamaAILLM {
     return { safe: true, reasons: [] };
   }
 
-  async sendChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    const messages = await this.compressMessages(
-      {
-        systemPrompt: chatPrompt(workspace),
-        userPrompt: prompt,
-        chatHistory,
-      },
-      rawHistory
-    );
-
-    const model = this.#ollamaClient({
-      temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-    });
-    const textResponse = await model
-      .pipe(new StringOutputParser())
-      .invoke(this.#convertToLangchainPrototypes(messages))
-      .catch((e) => {
-        throw new Error(
-          `Ollama::getChatCompletion failed to communicate with Ollama. ${e.message}`
-        );
-      });
-
-    if (!textResponse || !textResponse.length)
-      throw new Error(`Ollama::sendChat text response was empty.`);
-
-    return textResponse;
-  }
-
-  async streamChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    const messages = await this.compressMessages(
-      {
-        systemPrompt: chatPrompt(workspace),
-        userPrompt: prompt,
-        chatHistory,
-      },
-      rawHistory
-    );
-
-    const model = this.#ollamaClient({
-      temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-    });
-    const stream = await model
-      .pipe(new StringOutputParser())
-      .stream(this.#convertToLangchainPrototypes(messages));
-    return stream;
-  }
-
   async getChatCompletion(messages = null, { temperature = 0.7 }) {
     const model = this.#ollamaClient({ temperature });
     const textResponse = await model
diff --git a/server/utils/AiProviders/openAi/index.js b/server/utils/AiProviders/openAi/index.js
index d69ec11e..3a4d997c 100644
--- a/server/utils/AiProviders/openAi/index.js
+++ b/server/utils/AiProviders/openAi/index.js
@@ -1,5 +1,4 @@
 const { OpenAiEmbedder } = require("../../EmbeddingEngines/openAi");
-const { chatPrompt } = require("../../chats");
 const {
   handleDefaultStreamResponseV2,
 } = require("../../helpers/chat/responses");
@@ -41,7 +40,7 @@ class OpenAiLLM {
   }
 
   streamingEnabled() {
-    return "streamChat" in this && "streamGetChatCompletion" in this;
+    return "streamGetChatCompletion" in this;
   }
 
   promptWindowLimit() {
@@ -122,65 +121,6 @@ class OpenAiLLM {
     return { safe: false, reasons };
   }
 
-  async sendChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    if (!(await this.isValidChatCompletionModel(this.model)))
-      throw new Error(
-        `OpenAI chat: ${this.model} is not valid for chat completion!`
-      );
-
-    const textResponse = await this.openai.chat.completions
-      .create({
-        model: this.model,
-        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-        n: 1,
-        messages: await this.compressMessages(
-          {
-            systemPrompt: chatPrompt(workspace),
-            userPrompt: prompt,
-            chatHistory,
-          },
-          rawHistory
-        ),
-      })
-      .then((result) => {
-        if (!result.hasOwnProperty("choices"))
-          throw new Error("OpenAI chat: No results!");
-        if (result.choices.length === 0)
-          throw new Error("OpenAI chat: No results length!");
-        return result.choices[0].message.content;
-      })
-      .catch((error) => {
-        throw new Error(
-          `OpenAI::createChatCompletion failed with: ${error.message}`
-        );
-      });
-
-    return textResponse;
-  }
-
-  async streamChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    if (!(await this.isValidChatCompletionModel(this.model)))
-      throw new Error(
-        `OpenAI chat: ${this.model} is not valid for chat completion!`
-      );
-
-    const streamRequest = await this.openai.chat.completions({
-      model: this.model,
-      stream: true,
-      temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-      n: 1,
-      messages: await this.compressMessages(
-        {
-          systemPrompt: chatPrompt(workspace),
-          userPrompt: prompt,
-          chatHistory,
-        },
-        rawHistory
-      ),
-    });
-    return streamRequest;
-  }
-
   async getChatCompletion(messages = null, { temperature = 0.7 }) {
     if (!(await this.isValidChatCompletionModel(this.model)))
       throw new Error(
diff --git a/server/utils/AiProviders/openRouter/index.js b/server/utils/AiProviders/openRouter/index.js
index 8fb078fb..a8301083 100644
--- a/server/utils/AiProviders/openRouter/index.js
+++ b/server/utils/AiProviders/openRouter/index.js
@@ -1,10 +1,8 @@
 const { NativeEmbedder } = require("../../EmbeddingEngines/native");
-const { chatPrompt } = require("../../chats");
 const { v4: uuidv4 } = require("uuid");
 const {
   writeResponseChunk,
   clientAbortedHandler,
-  handleDefaultStreamResponseV2,
 } = require("../../helpers/chat/responses");
 const fs = require("fs");
 const path = require("path");
@@ -99,7 +97,7 @@ class OpenRouterLLM {
   }
 
   streamingEnabled() {
-    return "streamChat" in this && "streamGetChatCompletion" in this;
+    return "streamGetChatCompletion" in this;
   }
 
   promptWindowLimit() {
@@ -131,65 +129,6 @@ class OpenRouterLLM {
     return { safe: true, reasons: [] };
   }
 
-  async sendChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    if (!(await this.isValidChatCompletionModel(this.model)))
-      throw new Error(
-        `OpenRouter chat: ${this.model} is not valid for chat completion!`
-      );
-
-    const textResponse = await this.openai.chat.completions
-      .create({
-        model: this.model,
-        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-        n: 1,
-        messages: await this.compressMessages(
-          {
-            systemPrompt: chatPrompt(workspace),
-            userPrompt: prompt,
-            chatHistory,
-          },
-          rawHistory
-        ),
-      })
-      .then((result) => {
-        if (!result.hasOwnProperty("choices"))
-          throw new Error("OpenRouter chat: No results!");
-        if (result.choices.length === 0)
-          throw new Error("OpenRouter chat: No results length!");
-        return result.choices[0].message.content;
-      })
-      .catch((error) => {
-        throw new Error(
-          `OpenRouter::createChatCompletion failed with: ${error.message}`
-        );
-      });
-
-    return textResponse;
-  }
-
-  async streamChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    if (!(await this.isValidChatCompletionModel(this.model)))
-      throw new Error(
-        `OpenRouter chat: ${this.model} is not valid for chat completion!`
-      );
-
-    const streamRequest = await this.openai.chat.completions.create({
-      model: this.model,
-      stream: true,
-      temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-      n: 1,
-      messages: await this.compressMessages(
-        {
-          systemPrompt: chatPrompt(workspace),
-          userPrompt: prompt,
-          chatHistory,
-        },
-        rawHistory
-      ),
-    });
-    return streamRequest;
-  }
-
   async getChatCompletion(messages = null, { temperature = 0.7 }) {
     if (!(await this.isValidChatCompletionModel(this.model)))
       throw new Error(
@@ -304,143 +243,6 @@ class OpenRouterLLM {
     });
   }
 
-  // handleStream(response, stream, responseProps) {
-  //   const timeoutThresholdMs = 500;
-  //   const { uuid = uuidv4(), sources = [] } = responseProps;
-
-  //   return new Promise((resolve) => {
-  //     let fullText = "";
-  //     let chunk = "";
-  //     let lastChunkTime = null; // null when first token is still not received.
-
-  //     // Establish listener to early-abort a streaming response
-  //     // in case things go sideways or the user does not like the response.
-  //     // We preserve the generated text but continue as if chat was completed
-  //     // to preserve previously generated content.
-  //     const handleAbort = () => clientAbortedHandler(resolve, fullText);
-  //     response.on("close", handleAbort);
-
-  //     // NOTICE: Not all OpenRouter models will return a stop reason
-  //     // which keeps the connection open and so the model never finalizes the stream
-  //     // like the traditional OpenAI response schema does. So in the case the response stream
-  //     // never reaches a formal close state we maintain an interval timer that if we go >=timeoutThresholdMs with
-  //     // no new chunks then we kill the stream and assume it to be complete. OpenRouter is quite fast
-  //     // so this threshold should permit most responses, but we can adjust `timeoutThresholdMs` if
-  //     // we find it is too aggressive.
-  //     const timeoutCheck = setInterval(() => {
-  //       if (lastChunkTime === null) return;
-
-  //       const now = Number(new Date());
-  //       const diffMs = now - lastChunkTime;
-  //       if (diffMs >= timeoutThresholdMs) {
-  //         console.log(
-  //           `OpenRouter stream did not self-close and has been stale for >${timeoutThresholdMs}ms. Closing response stream.`
-  //         );
-  //         writeResponseChunk(response, {
-  //           uuid,
-  //           sources,
-  //           type: "textResponseChunk",
-  //           textResponse: "",
-  //           close: true,
-  //           error: false,
-  //         });
-  //         clearInterval(timeoutCheck);
-  //         response.removeListener("close", handleAbort);
-  //         resolve(fullText);
-  //       }
-  //     }, 500);
-
-  //     stream.data.on("data", (data) => {
-  //       const lines = data
-  //         ?.toString()
-  //         ?.split("\n")
-  //         .filter((line) => line.trim() !== "");
-
-  //       for (const line of lines) {
-  //         let validJSON = false;
-  //         const message = chunk + line.replace(/^data: /, "");
-
-  //         // JSON chunk is incomplete and has not ended yet
-  //         // so we need to stitch it together. You would think JSON
-  //         // chunks would only come complete - but they don't!
-  //         try {
-  //           JSON.parse(message);
-  //           validJSON = true;
-  //         } catch { }
-
-  //         if (!validJSON) {
-  //           // It can be possible that the chunk decoding is running away
-  //           // and the message chunk fails to append due to string length.
-  //           // In this case abort the chunk and reset so we can continue.
-  //           // ref: https://github.com/Mintplex-Labs/anything-llm/issues/416
-  //           try {
-  //             chunk += message;
-  //           } catch (e) {
-  //             console.error(`Chunk appending error`, e);
-  //             chunk = "";
-  //           }
-  //           continue;
-  //         } else {
-  //           chunk = "";
-  //         }
-
-  //         if (message == "[DONE]") {
-  //           lastChunkTime = Number(new Date());
-  //           writeResponseChunk(response, {
-  //             uuid,
-  //             sources,
-  //             type: "textResponseChunk",
-  //             textResponse: "",
-  //             close: true,
-  //             error: false,
-  //           });
-  //           clearInterval(timeoutCheck);
-  //           response.removeListener("close", handleAbort);
-  //           resolve(fullText);
-  //         } else {
-  //           let finishReason = null;
-  //           let token = "";
-  //           try {
-  //             const json = JSON.parse(message);
-  //             token = json?.choices?.[0]?.delta?.content;
-  //             finishReason = json?.choices?.[0]?.finish_reason || null;
-  //           } catch {
-  //             continue;
-  //           }
-
-  //           if (token) {
-  //             fullText += token;
-  //             lastChunkTime = Number(new Date());
-  //             writeResponseChunk(response, {
-  //               uuid,
-  //               sources: [],
-  //               type: "textResponseChunk",
-  //               textResponse: token,
-  //               close: false,
-  //               error: false,
-  //             });
-  //           }
-
-  //           if (finishReason !== null) {
-  //             lastChunkTime = Number(new Date());
-  //             writeResponseChunk(response, {
-  //               uuid,
-  //               sources,
-  //               type: "textResponseChunk",
-  //               textResponse: "",
-  //               close: true,
-  //               error: false,
-  //             });
-  //             clearInterval(timeoutCheck);
-  //             response.removeListener("close", handleAbort);
-  //             resolve(fullText);
-  //           }
-  //         }
-  //       }
-  //     });
-  //   });
-  // }
-
   // Simple wrapper for dynamic embedder & normalize interface for all LLM implementations
   async embedTextInput(textInput) {
     return await this.embedder.embedTextInput(textInput);
diff --git a/server/utils/AiProviders/perplexity/index.js b/server/utils/AiProviders/perplexity/index.js
index 71b74e9e..a17ec43f 100644
--- a/server/utils/AiProviders/perplexity/index.js
+++ b/server/utils/AiProviders/perplexity/index.js
@@ -1,5 +1,4 @@
 const { NativeEmbedder } = require("../../EmbeddingEngines/native");
-const { chatPrompt } = require("../../chats");
 const {
   handleDefaultStreamResponseV2,
 } = require("../../helpers/chat/responses");
@@ -50,7 +49,7 @@ class PerplexityLLM {
   }
 
   streamingEnabled() {
-    return "streamChat" in this && "streamGetChatCompletion" in this;
+    return "streamGetChatCompletion" in this;
   }
 
   promptWindowLimit() {
@@ -81,65 +80,6 @@ class PerplexityLLM {
     return { safe: true, reasons: [] };
   }
 
-  async sendChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    if (!(await this.isValidChatCompletionModel(this.model)))
-      throw new Error(
-        `Perplexity chat: ${this.model} is not valid for chat completion!`
-      );
-
-    const textResponse = await this.openai.chat.completions
-      .create({
-        model: this.model,
-        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-        n: 1,
-        messages: await this.compressMessages(
-          {
-            systemPrompt: chatPrompt(workspace),
-            userPrompt: prompt,
-            chatHistory,
-          },
-          rawHistory
-        ),
-      })
-      .then((result) => {
-        if (!result.hasOwnProperty("choices"))
-          throw new Error("Perplexity chat: No results!");
-        if (result.choices.length === 0)
-          throw new Error("Perplexity chat: No results length!");
-        return result.choices[0].message.content;
-      })
-      .catch((error) => {
-        throw new Error(
-          `Perplexity::createChatCompletion failed with: ${error.message}`
-        );
-      });
-
-    return textResponse;
-  }
-
-  async streamChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    if (!(await this.isValidChatCompletionModel(this.model)))
-      throw new Error(
-        `Perplexity chat: ${this.model} is not valid for chat completion!`
-      );
-
-    const streamRequest = await this.openai.chat.completions.create({
-      model: this.model,
-      stream: true,
-      temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-      n: 1,
-      messages: await this.compressMessages(
-        {
-          systemPrompt: chatPrompt(workspace),
-          userPrompt: prompt,
-          chatHistory,
-        },
-        rawHistory
-      ),
-    });
-    return streamRequest;
-  }
-
   async getChatCompletion(messages = null, { temperature = 0.7 }) {
     if (!(await this.isValidChatCompletionModel(this.model)))
       throw new Error(
diff --git a/server/utils/AiProviders/togetherAi/index.js b/server/utils/AiProviders/togetherAi/index.js
index 6d91e9a9..577a4b74 100644
--- a/server/utils/AiProviders/togetherAi/index.js
+++ b/server/utils/AiProviders/togetherAi/index.js
@@ -1,4 +1,3 @@
-const { chatPrompt } = require("../../chats");
 const {
   handleDefaultStreamResponseV2,
 } = require("../../helpers/chat/responses");
@@ -49,7 +48,7 @@ class TogetherAiLLM {
   }
 
   streamingEnabled() {
-    return "streamChat" in this && "streamGetChatCompletion" in this;
+    return "streamGetChatCompletion" in this;
   }
 
   // Ensure the user set a value for the token limit
@@ -82,65 +81,6 @@ class TogetherAiLLM {
     return { safe: true, reasons: [] };
   }
 
-  async sendChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    if (!(await this.isValidChatCompletionModel(this.model)))
-      throw new Error(
-        `Together AI chat: ${this.model} is not valid for chat completion!`
-      );
-
-    const textResponse = await this.openai.chat.completions
-      .create({
-        model: this.model,
-        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-        n: 1,
-        messages: await this.compressMessages(
-          {
-            systemPrompt: chatPrompt(workspace),
-            userPrompt: prompt,
-            chatHistory,
-          },
-          rawHistory
-        ),
-      })
-      .then((result) => {
-        if (!result.hasOwnProperty("choices"))
-          throw new Error("Together AI chat: No results!");
-        if (result.choices.length === 0)
-          throw new Error("Together AI chat: No results length!");
-        return result.choices[0].message.content;
-      })
-      .catch((error) => {
-        throw new Error(
-          `TogetherAI::createChatCompletion failed with: ${error.message}`
-        );
-      });
-
-    return textResponse;
-  }
-
-  async streamChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
-    if (!(await this.isValidChatCompletionModel(this.model)))
-      throw new Error(
-        `TogetherAI chat: ${this.model} is not valid for chat completion!`
-      );
-
-    const streamRequest = await this.openai.chat.completions.create({
-      model: this.model,
-      stream: true,
-      temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
-      n: 1,
-      messages: await this.compressMessages(
-        {
-          systemPrompt: chatPrompt(workspace),
-          userPrompt: prompt,
-          chatHistory,
-        },
-        rawHistory
-      ),
-    });
-    return streamRequest;
-  }
-
   async getChatCompletion(messages = null, { temperature = 0.7 }) {
     if (!(await this.isValidChatCompletionModel(this.model)))
       throw new Error(