Fixed request length bug, changed to as less used port

application/.env_sample

@@ -3,7 +3,7 @@ EMBEDDINGS_KEY=your_api_key
 CELERY_BROKER_URL=redis://localhost:6379/0
 CELERY_RESULT_BACKEND=redis://localhost:6379/1
 MONGO_URI=mongodb://localhost:27017/docsgpt
-API_URL=http://localhost:5001
+API_URL=http://localhost:7091
 
 #For OPENAI on Azure
 OPENAI_API_BASE=

application/Dockerfile

@@ -18,6 +18,6 @@ COPY . /app
 ENV FLASK_APP=app.py
 ENV FLASK_DEBUG=true
 
-EXPOSE 5001
+EXPOSE 7091
 
-CMD ["gunicorn", "-w", "2", "--timeout", "120", "--bind", "0.0.0.0:5001", "wsgi:app"]
+CMD ["gunicorn", "-w", "2", "--timeout", "120", "--bind", "0.0.0.0:7091", "wsgi:app"]

application/app.py

@@ -43,6 +43,7 @@ from worker import ingest_worker
 # os.environ["LANGCHAIN_HANDLER"] = "langchain"
 
 logger = logging.getLogger(__name__)
+gpt_model = 'gpt-3.5-turbo' # gpt-4
 
 if settings.LLM_NAME == "manifest":
     from manifest import Manifest
@@ -195,7 +196,7 @@ def complete_stream(question, docsearch, chat_history, api_key):
                     messages_combine.append({"role": "user", "content": i["prompt"]})
                     messages_combine.append({"role": "system", "content": i["response"]})
     messages_combine.append({"role": "user", "content": question})
-    completion = openai.ChatCompletion.create(model="gpt-3.5-turbo", engine=settings.AZURE_DEPLOYMENT_NAME,
+    completion = openai.ChatCompletion.create(model=gpt_model, engine=settings.AZURE_DEPLOYMENT_NAME,
                                               messages=messages_combine, stream=True, max_tokens=500, temperature=0)
 
     for line in completion:
@@ -208,26 +209,27 @@ def complete_stream(question, docsearch, chat_history, api_key):
     yield f"data: {data}\n\n"
 
 
-@app.route("/stream", methods=["POST", "GET"])
+@app.route("/stream", methods=["POST"])
 def stream():
+    data = request.get_json()
     # get parameter from url question
-    question = request.args.get("question")
-    history = request.args.get("history")
+    question = data["question"]
+    history = data["history"]
     # history to json object from string
     history = json.loads(history)
 
     # check if active_docs is set
 
     if not api_key_set:
-        api_key = request.args.get("api_key")
+        api_key = data["api_key"]
     else:
         api_key = settings.API_KEY
     if not embeddings_key_set:
-        embeddings_key = request.args.get("embeddings_key")
+        embeddings_key = data["embeddings_key"]
     else:
         embeddings_key = settings.EMBEDDINGS_KEY
-    if "active_docs" in request.args:
-        vectorstore = get_vectorstore({"active_docs": request.args.get("active_docs")})
+    if "active_docs" in data:
+        vectorstore = get_vectorstore({"active_docs": data["active_docs"]})
     else:
         vectorstore = ""
     docsearch = get_docsearch(vectorstore, embeddings_key)
@@ -279,7 +281,7 @@ def api_answer():
                 )
             else:
                 logger.debug("plain OpenAI")
-                llm = ChatOpenAI(openai_api_key=api_key)  # optional parameter: model_name="gpt-4"
+                llm = ChatOpenAI(openai_api_key=api_key, model_name=gpt_model)  # optional parameter: model_name="gpt-4"
             messages_combine = [SystemMessagePromptTemplate.from_template(chat_combine_template)]
             if history:
                 tokens_current_history = 0
@@ -597,4 +599,4 @@ def after_request(response):
 
 
 if __name__ == "__main__":
-    app.run(debug=True, port=5001)
+    app.run(debug=True, port=7091)

application/core/settings.py

@@ -12,7 +12,7 @@ class Settings(BaseSettings):
     MODEL_PATH: str = "./models/gpt4all-model.bin"
     TOKENS_MAX_HISTORY: int = 150
 
-    API_URL: str = "http://localhost:5001"  # backend url for celery worker
+    API_URL: str = "http://localhost:7091"  # backend url for celery worker
 
     API_KEY: str = None  # LLM api key
     EMBEDDINGS_KEY: str = None  # api key for embeddings (if using openai, just copy API_KEY

application/wsgi.py

@@ -1,4 +1,4 @@
 from app import app
 
 if __name__ == "__main__":
-    app.run(debug=True, port=5001)
+    app.run(debug=True, port=7091)