github-starred/awesome-llm-apps
2
0
Fork 0
mirror of https://github.com/Shubhamsaboo/awesome-llm-apps.git synced 2026-04-30 15:20:47 -05:00
Code Issues 25 Packages Projects Releases Wiki Activity

Address Copilot code review feedback

Browse Source 
Fixes applied:
- Fix NEO4J_PLUGINS JSON syntax in docker-compose.yml
- Fix directory name mismatch in README.md
- Remove unused imports (Any, Optional), add re and os
- Use Tuple from typing instead of lowercase tuple
- Move 're' import to module level (PEP 8)
- Configure Ollama client with OLLAMA_HOST env var for Docker
- Fix Cypher injection: use parameterized query for hops
- Make CONTAINS queries case-insensitive with toLower()
- Add try-finally block to ensure graph.close() on exceptions
This commit is contained in:
BIBIN PRATHAP
2026-01-03 04:50:22 -05:00
parent 380ae4a590
commit a650de1313
3 changed files with 15 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
rag_tutorials/knowledge_graph_rag_citations/README.md
View File

@@ -47,7 +47,7 @@ Traditional vector-based RAG finds similar text chunks, but struggles with:
```bash ```bash
# Clone and navigate # Clone and navigate
cd knowledge_graph_rag_with_citations cd knowledge_graph_rag_citations
# Install dependencies # Install dependencies
pip install -r requirements.txt pip install -r requirements.txt

2
rag_tutorials/knowledge_graph_rag_citations/docker-compose.yml
View File

@@ -9,7 +9,7 @@ services:
- "7687:7687" # Bolt - "7687:7687" # Bolt
environment: environment:
- NEO4J_AUTH=neo4j/password - NEO4J_AUTH=neo4j/password
- NEO4J_PLUGINS=["apoc"] - NEO4J_PLUGINS='["apoc"]'
volumes: volumes:
- neo4j_data:/data - neo4j_data:/data
healthcheck: healthcheck:

20
rag_tutorials/knowledge_graph_rag_citations/knowledge_graph_rag.py
View File

@@ -11,12 +11,19 @@ This example uses Ollama for local LLM inference and Neo4j for the knowledge gra
import streamlit as st import streamlit as st
import ollama import ollama
from ollama import Client as OllamaClient
from neo4j import GraphDatabase from neo4j import GraphDatabase
from typing import List, Dict, Any, Optional from typing import List, Dict, Tuple
import re
import os
from dataclasses import dataclass from dataclasses import dataclass
import json import json
import hashlib import hashlib
# Configure Ollama host from environment (for Docker)
OLLAMA_HOST = os.environ.get('OLLAMA_HOST', 'http://localhost:11434')
ollama_client = OllamaClient(host=OLLAMA_HOST)
# ============================================================================ # ============================================================================
# Data Models # Data Models
@@ -123,7 +130,7 @@ class KnowledgeGraphManager:
result = session.run( result = session.run(
f""" f"""
MATCH path = (start:Entity)-[*1..{hops}]-(related:Entity) MATCH path = (start:Entity)-[*1..{hops}]-(related:Entity)
WHERE start.name CONTAINS $name OR start.description CONTAINS $name WHERE toLower(start.name) CONTAINS toLower($name) OR toLower(start.description) CONTAINS toLower($name)
RETURN related.name as name, RETURN related.name as name,
related.description as description, related.description as description,
related.source_doc as source, related.source_doc as source,
@@ -131,7 +138,7 @@ class KnowledgeGraphManager:
[r in relationships(path) | r.description] as path_descriptions [r in relationships(path) | r.description] as path_descriptions
LIMIT 20 LIMIT 20
""", """,
name=entity_name name=entity_name, hops=hops
) )
return [dict(record) for record in result] return [dict(record) for record in result]
@@ -160,7 +167,7 @@ class KnowledgeGraphManager:
# LLM-based Entity Extraction # LLM-based Entity Extraction
# ============================================================================ # ============================================================================
def extract_entities_with_llm(text: str, source_doc: str, model: str = "llama3.2") -> tuple[List[Entity], List[Relationship]]: def extract_entities_with_llm(text: str, source_doc: str, model: str = "llama3.2") -> Tuple[List[Entity], List[Relationship]]:
"""Use LLM to extract entities and relationships from text.""" """Use LLM to extract entities and relationships from text."""
extraction_prompt = f"""Analyze the following text and extract: extraction_prompt = f"""Analyze the following text and extract:
@@ -193,7 +200,7 @@ Respond in JSON format:
""" """
try: try:
response = ollama.chat( response = ollama_client.chat(
model=model, model=model,
messages=[{"role": "user", "content": extraction_prompt}], messages=[{"role": "user", "content": extraction_prompt}],
format="json" format="json"
@@ -306,7 +313,7 @@ Provide a comprehensive answer with inline citations [1], [2], etc. for each cla
""" """
try: try:
response = ollama.chat( response = ollama_client.chat(
model=model, model=model,
messages=[{"role": "user", "content": answer_prompt}] messages=[{"role": "user", "content": answer_prompt}]
) )
@@ -314,7 +321,6 @@ Provide a comprehensive answer with inline citations [1], [2], etc. for each cla
reasoning_trace.append("✅ Generated answer with citations") reasoning_trace.append("✅ Generated answer with citations")
# Step 5: Extract and verify citations # Step 5: Extract and verify citations
import re
citation_refs = re.findall(r'\[(\d+)\]', answer) citation_refs = re.findall(r'\[(\d+)\]', answer)
for ref in set(citation_refs): for ref in set(citation_refs):