vrr/SurfSense
2
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2025-09-02 10:39:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: cleanup

Browse source
This commit is contained in:
DESKTOP-RTLN3BA\$punk 2025-04-20 23:34:21 -07:00
parent 82a4eb3966
commit a1aad295bb
4 changed files with 16 additions and 23 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
README.md
View file

@ -119,13 +119,13 @@ This is the core of SurfSense. Before we begin let's look at `.env` variables' t
| EMBEDDING_MODEL| Name of the embedding model to use for vector embeddings. Currently works with Sentence Transformers only. Expect other embeddings soon. Eg. `mixedbread-ai/mxbai-embed-large-v1`| | EMBEDDING_MODEL| Name of the embedding model to use for vector embeddings. Currently works with Sentence Transformers only. Expect other embeddings soon. Eg. `mixedbread-ai/mxbai-embed-large-v1`|
| RERANKERS_MODEL_NAME| Name of the reranker model for search result reranking. Eg. `ms-marco-MiniLM-L-12-v2`| | RERANKERS_MODEL_NAME| Name of the reranker model for search result reranking. Eg. `ms-marco-MiniLM-L-12-v2`|
| RERANKERS_MODEL_TYPE| Type of reranker model being used. Eg. `flashrank`| | RERANKERS_MODEL_TYPE| Type of reranker model being used. Eg. `flashrank`|
| FAST_LLM| LiteLLM routed Smaller, faster LLM for quick responses. Eg. `litellm:openai/gpt-4o`| | FAST_LLM| LiteLLM routed Smaller, faster LLM for quick responses. Eg. `openai/gpt-4o-mini`, `ollama/deepseek-r1:8b`|
| STRATEGIC_LLM| LiteLLM routed Advanced LLM for complex reasoning tasks. Eg. `litellm:openai/gpt-4o`| | STRATEGIC_LLM| LiteLLM routed Advanced LLM for complex reasoning tasks. Eg. `openai/gpt-4o`, `ollama/gemma3:12b`|
| LONG_CONTEXT_LLM| LiteLLM routed LLM capable of handling longer context windows. Eg. `litellm:gemini/gemini-2.0-flash`| | LONG_CONTEXT_LLM| LiteLLM routed LLM capable of handling longer context windows. Eg. `gemini/gemini-2.0-flash`, `ollama/deepseek-r1:8b`|
| UNSTRUCTURED_API_KEY| API key for Unstructured.io service for document parsing| | UNSTRUCTURED_API_KEY| API key for Unstructured.io service for document parsing|
| FIRECRAWL_API_KEY| API key for Firecrawl service for web crawling and data extraction| | FIRECRAWL_API_KEY| API key for Firecrawl service for web crawling and data extraction|
IMPORTANT: Since LLM calls are routed through LiteLLM make sure to include API keys of LLM models you are using. For example if you used `litellm:openai/gpt-4o` make sure to include OpenAI API Key `OPENAI_API_KEY` or if you use `litellm:gemini/gemini-2.0-flash` then you include `GEMINI_API_KEY`. IMPORTANT: Since LLM calls are routed through LiteLLM make sure to include API keys of LLM models you are using. For example if you used `openai/gpt-4o` make sure to include OpenAI API Key `OPENAI_API_KEY` or if you use `gemini/gemini-2.0-flash` then you include `GEMINI_API_KEY`.
You can also integrate any LLM just follow this https://docs.litellm.ai/docs/providers You can also integrate any LLM just follow this https://docs.litellm.ai/docs/providers

9
surfsense_backend/.env.example
View file

@ -4,15 +4,18 @@ SECRET_KEY="SECRET"
GOOGLE_OAUTH_CLIENT_ID="924507538m" GOOGLE_OAUTH_CLIENT_ID="924507538m"
GOOGLE_OAUTH_CLIENT_SECRET="GOCSV" GOOGLE_OAUTH_CLIENT_SECRET="GOCSV"
NEXT_FRONTEND_URL="http://localhost:3000" NEXT_FRONTEND_URL="http://localhost:3000"
EMBEDDING_MODEL="mixedbread-ai/mxbai-embed-large-v1" EMBEDDING_MODEL="mixedbread-ai/mxbai-embed-large-v1"
RERANKERS_MODEL_NAME="ms-marco-MiniLM-L-12-v2" RERANKERS_MODEL_NAME="ms-marco-MiniLM-L-12-v2"
RERANKERS_MODEL_TYPE="flashrank" RERANKERS_MODEL_TYPE="flashrank"
FAST_LLM="litellm:openai/gpt-4o-mini" # https://docs.litellm.ai/docs/providers
STRATEGIC_LLM="litellm:openai/gpt-4o" FAST_LLM="openai/gpt-4o-mini"
LONG_CONTEXT_LLM="litellm:gemini/gemini-2.0-flash" STRATEGIC_LLM="openai/gpt-4o"
LONG_CONTEXT_LLM="gemini/gemini-2.0-flash"
# Chosen LiteLLM Providers Keys
OPENAI_API_KEY="sk-proj-iA" OPENAI_API_KEY="sk-proj-iA"
GEMINI_API_KEY="AIzaSyB6-1641124124124124124124124124124" GEMINI_API_KEY="AIzaSyB6-1641124124124124124124124124124"

3
surfsense_backend/app/agents/researcher/sub_section_writer/nodes.py
View file

@ -37,7 +37,8 @@ async def rerank_documents(state: State, config: RunnableConfig) -> Dict[str, An
if reranker_service: if reranker_service:
try: try:
# Use the sub-section questions for reranking context # Use the sub-section questions for reranking context
rerank_query = "\n".join(sub_section_questions) # rerank_query = "\n".join(sub_section_questions)
rerank_query = configuration.user_query
# Convert documents to format expected by reranker if needed # Convert documents to format expected by reranker if needed
reranker_input_docs = [ reranker_input_docs = [

17
surfsense_backend/app/config/__init__.py
View file

@ -15,17 +15,6 @@ env_file = BASE_DIR / ".env"
load_dotenv(env_file) load_dotenv(env_file)
def extract_model_name(llm_string: str) -> str:
"""Extract the model name from an LLM string.
Example: "litellm:openai/gpt-4o-mini" -> "openai/gpt-4o-mini"
Args:
llm_string: The LLM string with optional prefix
Returns:
str: The extracted model name
"""
return llm_string.split(":", 1)[1] if ":" in llm_string else llm_string
class Config: class Config:
# Database # Database
@ -38,13 +27,13 @@ class Config:
# LONG-CONTEXT LLMS # LONG-CONTEXT LLMS
LONG_CONTEXT_LLM = os.getenv("LONG_CONTEXT_LLM") LONG_CONTEXT_LLM = os.getenv("LONG_CONTEXT_LLM")
long_context_llm_instance = ChatLiteLLM(model=extract_model_name(LONG_CONTEXT_LLM)) long_context_llm_instance = ChatLiteLLM(model=LONG_CONTEXT_LLM)
# GPT Researcher # GPT Researcher
FAST_LLM = os.getenv("FAST_LLM") FAST_LLM = os.getenv("FAST_LLM")
STRATEGIC_LLM = os.getenv("STRATEGIC_LLM") STRATEGIC_LLM = os.getenv("STRATEGIC_LLM")
fast_llm_instance = ChatLiteLLM(model=extract_model_name(FAST_LLM)) fast_llm_instance = ChatLiteLLM(model=FAST_LLM)
strategic_llm_instance = ChatLiteLLM(model=extract_model_name(STRATEGIC_LLM)) strategic_llm_instance = ChatLiteLLM(model=STRATEGIC_LLM)
# Chonkie Configuration | Edit this to your needs # Chonkie Configuration | Edit this to your needs