llama

main.py

@@ -2,6 +2,7 @@ import io
 import os
 import json
 
+import requests
 from openai import OpenAI
 from flask import Flask, request, jsonify, send_from_directory, url_for
 
@@ -97,7 +98,7 @@ def vision(message, image_url=None, image_b64=None):
         chat_messages.append(json_payload)
         print(chat_messages)
         json_response = app.openai_client.chat.completions.create(
-            model="gpt-4-vision-preview",
+            model="gpt-4o",
             messages=chat_messages,
             max_tokens=500
         )
@@ -151,7 +152,7 @@ def gpt():
                 if summarize:
                     chat_messages = app.summary_messages.copy()
                     max_char_msg = 2000
-                    max_resp_token = 4096
+                    max_resp_token = 1000
                 else:
                     chat_messages = app.chat_messages.copy()
                 json_payload['payload'][-1]['content'] = f"Please summarize this article:\n" + \
@@ -174,7 +175,7 @@ def gpt():
             islamic_response = app.openai_client.chat.completions.create(model="gpt-3.5-turbo",  # GPT-3.5 Turbo engine
                                                                          messages=islam_messages,
                                                                          max_tokens=2, temperature=0.5)
-            if 'Ya' in islamic_response.choices[0].message['content']:
+            if 'Ya' in islamic_response.choices[0].message.content:
                 greeting_message = f"Buatkan respons chatbot berupa greeting dari chat perusahaan bernama {company_name} pada jam {timestamp}, tidak perlu mention waktu, dan jawab dengan 'Assalamu'alaikum...' terlebih dahulu"
             else:
                 greeting_message = f"Buatkan respons chatbot berupa greeting dari chat perusahaan bernama {company_name} pada jam {timestamp}, tidak perlu mention waktu"
@@ -273,7 +274,7 @@ def train():
                     "n_epochs": 5
                 }
             )
-            app.logger.info({"mock": "yes", "status": job.status, "job_id": job.id})
+            app.logger.info({"mock": "no", "status": job.status, "job_id": job.id})
             return {"status": job.status, "job_id": job.id}
         else:
             app.logger.info({"mock": "yes", "status": "ok"})
@@ -295,6 +296,52 @@ def train_with_id(job_id):
         app.logger.error(error_print)
         return {"status": "Could not find job from id"}
 
+@app.route('/llama', methods=['POST'])
+def llama():
+    max_char_msg = 500
+    max_resp_token = 600
+    json_payload = request.get_json()
+    if not json_payload:
+        json_payload = []
+    has_named_params = False
+    if isinstance(json_payload, dict):
+        has_named_params = 'payload' in json_payload
+        if 'payload' in json_payload:
+            json_payload = json_payload['payload']
+            if isinstance(json_payload, dict):
+                json_payload = [json_payload]
+        else:
+            json_payload = [json_payload]
+    message = json_payload[-1]
+    content = message['content']
+    content_arr = content.split(" ")
+    new_content_arr = content[:max_char_msg].split(" ")
+    new_content_len = len(new_content_arr)
+    arr = []
+    for i in range(new_content_len):
+        arr.append(content_arr[i])
+    content = " ".join(arr)
+    content = content + " Jawab dengan Bahasa Indonesia"
+    try:
+        json_request = {
+            "model": "llama3",
+            "prompt": content,
+            "stream": False
+        }
+        r = requests.post("http://localhost:11434/api/generate", json=json_request)
+        if r.status_code == 200:
+            result = {
+                "role": "assistant",
+                "content": r.json()["response"]
+            }
+        else:
+            result = {}, r.status_code
+    except Exception as error_print:
+        app.logger.error(error_print)
+        result = {}, 405
+    return result
+
+
 
 # Press the green button in the gutter to run the script.
 if __name__ == '__main__':