Skip to content

Refactor agent and replace web search with local search #190

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
MaxAdmk wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Refactor agent and replace web search with local search #190

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
78dc42f
Refactor LLM usage to Groq (llama-3.3-70b-versatile) and harden resea…
MaxAdmk Jan 19, 2026
98f1613
Replaced external web search with a local markdown directory search.
MaxAdmk Jan 19, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 7 additions & 1 deletion backend/examples/cli_research.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,11 @@ def main() -> None:
"""Run the research agent from the command line."""
parser = argparse.ArgumentParser(description="Run the LangGraph research agent")
parser.add_argument("question", help="Research question")
parser.add_argument(
"--dir",
required=True,
help="Path to a local directory containing .md files for the agent to reference",
)
parser.add_argument(
"--initial-queries",
type=int,
Expand All @@ -21,13 +26,14 @@ def main() -> None:
)
parser.add_argument(
"--reasoning-model",
default="gemini-2.5-pro-preview-05-06",
default="llama-3.3-70b-versatile",
help="Model for the final answer",
)
args = parser.parse_args()

state = {
"messages": [HumanMessage(content=args.question)],
"docs_dir": args.dir,
"initial_search_query_count": args.initial_queries,
"max_research_loops": args.max_loops,
"reasoning_model": args.reasoning_model,
Expand Down
1 change: 1 addition & 0 deletions backend/pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@ dependencies = [
"langgraph>=0.2.6",
"langchain>=0.3.19",
"langchain-google-genai",
"langchain-groq",
"python-dotenv>=1.0.1",
"langgraph-sdk>=0.1.57",
"langgraph-cli",
Expand Down
19 changes: 13 additions & 6 deletions backend/src/agent/configuration.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,23 +9,30 @@ class Configuration(BaseModel):
"""The configuration for the agent."""

query_generator_model: str = Field(
default="gemini-2.0-flash",
default="llama-3.3-70b-versatile",
metadata={
"description": "The name of the language model to use for the agent's query generation."
"description": "Groq model name to use for the agent's query generation."
},
)

reflection_model: str = Field(
default="gemini-2.5-flash",
default="llama-3.3-70b-versatile",
metadata={
"description": "The name of the language model to use for the agent's reflection."
"description": "Groq model name to use for the agent's reflection."
},
)

answer_model: str = Field(
default="gemini-2.5-pro",
default="llama-3.3-70b-versatile",
metadata={
"description": "Groq model name to use for the agent's answer."
},
)

web_search_model: str = Field(
default="gemini-2.0-flash",
metadata={
"description": "The name of the language model to use for the agent's answer."
"description": "Gemini model name to use for Google Search grounding."
},
)
Comment on lines +32 to 37
Copy link

@gemini-code-assist gemini-code-assist bot Jan 21, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The web_search_model configuration field is defined but appears to be unused. The new local search implementation in the web_research node does not use an LLM. This field should be removed to avoid confusion and keep the configuration clean.


Expand Down
Loading