vikarti.anatra/Automated-AI-Web-Researcher-Ollama
1
0
Fork 0
mirror of https://github.com/TheBlewish/Automated-AI-Web-Researcher-Ollama.git synced 2025-09-14 09:19:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

added openai support

Browse source
This commit is contained in:
benx13 2024-11-21 08:57:30 -08:00
parent e3cb357c3b
commit b5117f37b5
4 changed files with 88 additions and 23 deletions
Download patch file Download diff file Expand all files Collapse all files

40
llm_config.py
View file

@ -1,29 +1,29 @@
# llm_config.py
LLM_TYPE = "ollama" # Options: 'llama_cpp', 'ollama'
LLM_TYPE = "openai" # Options: 'llama_cpp', 'ollama', 'openai'
# LLM settings for llama_cpp
MODEL_PATH = "/home/james/llama.cpp/models/gemma-2-9b-it-Q6_K.gguf" # Replace with your llama.cpp models filepath
MODEL_PATH = "/home/james/llama.cpp/models/gemma-2-9b-it-Q6_K.gguf"
LLM_CONFIG_LLAMA_CPP = {
"llm_type": "llama_cpp",
"model_path": MODEL_PATH,
"n_ctx": 20000, # context size
"n_gpu_layers": 0, # number of layers to offload to GPU (-1 for all, 0 for none)
"n_threads": 8, # number of threads to use
"temperature": 0.7, # temperature for sampling
"top_p": 0.9, # top p for sampling
"top_k": 40, # top k for sampling
"repeat_penalty": 1.1, # repeat penalty
"max_tokens": 1024, # max tokens to generate
"stop": ["User:", "\n\n"] # stop sequences
"n_ctx": 20000,
"n_gpu_layers": 0,
"n_threads": 8,
"temperature": 0.7,
"top_p": 0.9,
"top_k": 40,
"repeat_penalty": 1.1,
"max_tokens": 1024,
"stop": ["User:", "\n\n"]
}
# LLM settings for Ollama
LLM_CONFIG_OLLAMA = {
"llm_type": "ollama",
"base_url": "http://localhost:11434", # default Ollama server URL
"model_name": "custom-phi3-32k-Q4_K_M", # Replace with your Ollama model name
"base_url": "http://localhost:11434",
"model_name": "custom-phi3-32k-Q4_K_M",
"temperature": 0.7,
"top_p": 0.9,
"n_ctx": 55000,
@ -31,10 +31,24 @@ LLM_CONFIG_OLLAMA = {
"stop": ["User:", "\n\n"]
}
# New: LLM settings for OpenAI
LLM_CONFIG_OPENAI = {
"llm_type": "openai",
"model_name": "gpt-4o-mini",
"api_key": "",
"temperature": 0.7,
"top_p": 0.9,
"max_tokens": 4096,
"stop": ["User:", "\n\n"],
"context_length": 128000 # GPT-4 Turbo context window
}
def get_llm_config():
if LLM_TYPE == "llama_cpp":
return LLM_CONFIG_LLAMA_CPP
elif LLM_TYPE == "ollama":
return LLM_CONFIG_OLLAMA
elif LLM_TYPE == "openai":
return LLM_CONFIG_OPENAI
else:
raise ValueError(f"Invalid LLM_TYPE: {LLM_TYPE}")