From e9c0b605d0eb0c5ea495a6aca285e24b134ef47a Mon Sep 17 00:00:00 2001 From: MasterX Date: Sat, 17 Aug 2024 17:53:31 +0200 Subject: [PATCH 1/3] Update example.env Add OLLAMA_BASE_URL and LM_STUDIO_BASE_URL as a variable to the dotenv file. --- example.env | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/example.env b/example.env index 0c4e766dd..999939552 100644 --- a/example.env +++ b/example.env @@ -10,4 +10,7 @@ OPENAI_AZURE_ENDPOINT= OPENAI_API_VERSION= TOKENIZERS_PARALLELISM=true -PYDEVD_DISABLE_FILE_VALIDATION=1 \ No newline at end of file +PYDEVD_DISABLE_FILE_VALIDATION=1 + +OLLAMA_BASE_URL="http://127.0.0.1:11434" +LM_STUDIO_BASE_URL="http://127.0.0.1:1234/v1" \ No newline at end of file From cf34240e47f2de6139c64b38deb962afcd7c8456 Mon Sep 17 00:00:00 2001 From: MasterX Date: Sat, 17 Aug 2024 17:55:03 +0200 Subject: [PATCH 2/3] Update models.py Add OLLAMA_BASE_URL and LM_STUDIO_BASE_URL to the models.py file so both instances can be easily changed when using an installation on another or another docker container. --- models.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/models.py b/models.py index 33af468b3..4b4b06482 100644 --- a/models.py +++ b/models.py @@ -22,7 +22,7 @@ def get_api_key(service): # Ollama models -def get_ollama_chat(model_name:str, temperature=DEFAULT_TEMPERATURE, base_url="http://localhost:11434"): +def get_ollama_chat(model_name:str, temperature=DEFAULT_TEMPERATURE, base_url=os.getenv("OLLAMA_BASE_URL")): return Ollama(model=model_name,temperature=temperature, base_url=base_url) def get_ollama_embedding(model_name:str, temperature=DEFAULT_TEMPERATURE): @@ -34,10 +34,10 @@ def get_huggingface_embedding(model_name:str): return HuggingFaceEmbeddings(model_name=model_name) # LM Studio and other OpenAI compatible interfaces -def get_lmstudio_chat(model_name:str, base_url="http://localhost:1234/v1", temperature=DEFAULT_TEMPERATURE): +def get_lmstudio_chat(model_name:str, base_url=os.getenv("LM_STUDIO_BASE_URL"), temperature=DEFAULT_TEMPERATURE): return ChatOpenAI(model_name=model_name, base_url=base_url, temperature=temperature, api_key="none") # type: ignore -def get_lmstudio_embedding(model_name:str, base_url="http://localhost:1234/v1"): +def get_lmstudio_embedding(model_name:str, base_url=os.getenv("LM_STUDIO_BASE_URL")): return OpenAIEmbeddings(model_name=model_name, base_url=base_url) # type: ignore # Anthropic models From 779021000e1a1dc115a72d7e7f84e6e3d9302cae Mon Sep 17 00:00:00 2001 From: MasterX Date: Sat, 17 Aug 2024 19:10:46 +0200 Subject: [PATCH 3/3] Move more URL's to the dotenv file. Move more URL's to the dotenv file. --- example.env | 3 ++- models.py | 4 ++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/example.env b/example.env index 999939552..3dec96268 100644 --- a/example.env +++ b/example.env @@ -13,4 +13,5 @@ TOKENIZERS_PARALLELISM=true PYDEVD_DISABLE_FILE_VALIDATION=1 OLLAMA_BASE_URL="http://127.0.0.1:11434" -LM_STUDIO_BASE_URL="http://127.0.0.1:1234/v1" \ No newline at end of file +LM_STUDIO_BASE_URL="http://127.0.0.1:1234/v1" +OPEN_ROUTER_BASE_URL="https://openrouter.ai/api/v1" \ No newline at end of file diff --git a/models.py b/models.py index 4b4b06482..08532c037 100644 --- a/models.py +++ b/models.py @@ -86,8 +86,8 @@ def get_groq_chat(model_name:str, api_key=None, temperature=DEFAULT_TEMPERATURE) # OpenRouter models def get_openrouter(model_name: str="meta-llama/llama-3.1-8b-instruct:free", api_key=None, temperature=DEFAULT_TEMPERATURE): api_key = api_key or get_api_key("openrouter") - return ChatOpenAI(api_key=api_key, base_url="https://openrouter.ai/api/v1", model=model_name, temperature=temperature) # type: ignore - + return ChatOpenAI(api_key=api_key, base_url=os.getenv("OPEN_ROUTER_BASE_URL"), model=model_name, temperature=temperature) # type: ignore + def get_embedding_hf(model_name="sentence-transformers/all-MiniLM-L6-v2"): return HuggingFaceEmbeddings(model_name=model_name)