upgraded documentation

Dockerfile

@@ -7,7 +7,7 @@ RUN python3 -m venv venv && . venv/bin/activate
 RUN python3 -m pip install --no-cache-dir -r requirements.txt --upgrade pip
 
 COPY ./app.py /srv/app.py
-COPY ./pyGpt4All /srv/pyGpt4All
+COPY ./gpt4all_api /srv/gpt4all_api
 COPY ./backends /srv/backends
 COPY ./static /srv/static
 COPY ./templates /srv/templates

README.md

@@ -97,9 +97,10 @@ Now you're ready to work!
 
 # Supported backends
 Two backends are now supported:
-1 - [The llama_cpp backend](https://github.com/nomic-ai/pygpt4all)
+1 - [The llama_cpp backend by Abdeladim](https://github.com/abdeladim-s/pyllamacpp)
-2 - [The GPT-j backend](https://github.com/marella/gpt4all-j)
+2 - [The GPT-j backend by Abdeladim](https://github.com/abdeladim-s/pygptj)
-3 - Hugging face's Transformers (under construction)
+3 - [The GPT-j backend by marella](https://github.com/marella/gpt4all-j)
+4 - Hugging face's Transformers (under construction)
 
 # Supported models
 You can also refuse to download the model during the install procedure and download it manually.

backends/gpt_4all/__init__.py

@@ -35,9 +35,6 @@ class GPT4ALL(GPTBackend):
                 model_path=f"./models/gpt_4all/{self.config['model']}",
         )
 
-    def stop_generation(self):
-        self.model._grab_text_callback()
-
     def generate(self, 
                  prompt:str,                  
                  n_predict: int = 128,

backends/gpt_j/__init__.py

@@ -34,9 +34,6 @@ class GptJ(GPTBackend):
                 prompt_context="", prompt_prefix="", prompt_suffix=""
                 )
 
-    def stop_generation(self):
-        self.model._grab_text_callback()
-
     def generate(self, 
                  prompt:str,                  
                  n_predict: int = 128,

backends/gptj/__init__.py

@@ -34,9 +34,6 @@ class GPTJ(GPTBackend):
                 model=f"./models/llama_cpp/{self.config['model']}", avx2 = self.config["use_avx2"]
                 )
 
-    def stop_generation(self):
-        self.model._grab_text_callback()
-
     def generate(self, 
                  prompt:str,                  
                  n_predict: int = 128,

backends/gptq/__init__.py

@@ -11,7 +11,7 @@ from pathlib import Path
 from typing import Callable
 from transformers import AutoTokenizer, TextGenerationPipeline
 from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
-from pyGpt4All.backend import GPTBackend
+from gpt4all_api.backend import GPTBackend
 import torch
 import yaml
 
@@ -38,11 +38,6 @@ class GPTQ(GPTBackend):
         self.model = AutoGPTQForCausalLM.from_pretrained(self.model_dir, BaseQuantizeConfig())
         self.tokenizer = AutoTokenizer.from_pretrained(self.model_dir, use_fast=True    )
 
-
-
-    def stop_generation(self):
-        self.model._grab_text_callback()
-
     def generate(self, 
                  prompt:str,                  
                  n_predict: int = 128,

backends/hugging_face/__init__.py

@@ -13,7 +13,7 @@ from accelerate import init_empty_weights
 from accelerate import load_checkpoint_and_dispatch
 from transformers import AutoTokenizer
 from transformers import AutoConfig, AutoModelForCausalLM
-from pyGpt4All.backend import GPTBackend
+from gpt4all_api.backend import GPTBackend
 import torch
 
 __author__ = "parisneo"
@@ -39,10 +39,6 @@ class HuggingFace(GPTBackend):
         self.tokenizer = AutoTokenizer.from_pretrained(config["model"])
         self.model = AutoModelForCausalLM.from_pretrained(config["model"], load_in_8bit=True, device_map='auto')
 
-
-    def stop_generation(self):
-        self.model._grab_text_callback()
-
     def generate(self, 
                  prompt:str,                  
                  n_predict: int = 128,

backends/llama_cpp/__init__.py

@@ -37,9 +37,6 @@ class LLAMACPP(GPTBackend):
                 seed=self.config['seed'],
                 )
 
-    def stop_generation(self):
-        self.model._grab_text_callback()
-
     def generate(self, 
                  prompt:str,                  
                  n_predict: int = 128,

gpt4all_api/api.py

@@ -167,34 +167,39 @@ class ModelProcess:
                 time.sleep(1)
                 print(ex)
     def _generate(self, prompt, id, n_predict):
-        self.id = id        
+        if self.model is not None:
-        if self.config["override_personality_model_parameters"]:
+            self.id = id
-            self.model.generate(
+            if self.config["override_personality_model_parameters"]:
-                prompt,
+                self.model.generate(
-                new_text_callback=self._callback,
+                    prompt,
-                n_predict=n_predict,
+                    new_text_callback=self._callback,
-                temp=self.config['temperature'],
+                    n_predict=n_predict,
-                top_k=self.config['top_k'],
+                    temp=self.config['temperature'],
-                top_p=self.config['top_p'],
+                    top_k=self.config['top_k'],
-                repeat_penalty=self.config['repeat_penalty'],
+                    top_p=self.config['top_p'],
-                repeat_last_n = self.config['repeat_last_n'],
+                    repeat_penalty=self.config['repeat_penalty'],
-                seed=self.config['seed'],
+                    repeat_last_n = self.config['repeat_last_n'],
-                n_threads=self.config['n_threads']
+                    seed=self.config['seed'],
-            )
+                    n_threads=self.config['n_threads']
+                )
+            else:
+                self.model.generate(
+                    prompt,
+                    new_text_callback=self._callback,
+                    n_predict=n_predict,
+                    temp=self.personality.model_temperature,
+                    top_k=self.personality.model_top_k,
+                    top_p=self.personality.model_top_p,
+                    repeat_penalty=self.personality.model_repeat_penalty,
+                    repeat_last_n = self.personality.model_repeat_last_n,
+                    #seed=self.config['seed'],
+                    n_threads=self.config['n_threads']
+                )
         else:
-            self.model.generate(
+            print("No model is installed or selected. Please make sure to install a model and select it inside your configuration before attempting to communicate with the model.")
-                prompt,
+            print("To do this: Install the model to your models/<backend name> folder.")
-                new_text_callback=self._callback,
+            print("Then set your model information in your local configuration file that you can find in configs/local_default.yaml")
-                n_predict=n_predict,
+            print("You can also use the ui to set your model in the settings page.")
-                temp=self.personality.model_temperature,
-                top_k=self.personality.model_top_k,
-                top_p=self.personality.model_top_p,
-                repeat_penalty=self.personality.model_repeat_penalty,
-                repeat_last_n = self.personality.model_repeat_last_n,
-                #seed=self.config['seed'],
-                n_threads=self.config['n_threads']
-            )
-        
     def _callback(self, text):
         if not self.ready:
             print(".",end="")