Santosh Bhavani 12c4777eae feat(langchain): upgrade to Llama 3.3 Nemotron Super 49B ... - Update LangChain service to use Llama 3.3 Nemotron Super 49B v1.5 - Adjust temperature to 0.6 for better response quality - Increase timeout to 120s for larger model - Add top_p, frequency_penalty, and presence_penalty parameters - Remove deprecated response_format configuration		2025-10-19 20:57:03 -07:00
..
arangodb-loader.ts	chore: Regenerate all playbooks	2025-10-06 17:05:41 +00:00
arangodb.ts	chore: Regenerate all playbooks	2025-10-06 17:05:41 +00:00
backend-service.ts	feat(backend): implement LLM-enhanced query method	2025-10-19 19:57:12 -07:00
client-init.ts	chore: Regenerate all playbooks	2025-10-06 17:05:41 +00:00
embeddings.ts	chore: Regenerate all playbooks	2025-10-06 17:05:41 +00:00
graph-db-service.ts	chore: Regenerate all playbooks	2025-10-06 17:05:41 +00:00
graph-db-util.ts	chore: Regenerate all playbooks	2025-10-06 17:05:41 +00:00
langchain-service.ts	feat(langchain): upgrade to Llama 3.3 Nemotron Super 49B	2025-10-19 20:57:03 -07:00
llm-service.ts	chore: Regenerate all playbooks	2025-10-06 17:05:41 +00:00
neo4j.ts	chore: Regenerate all playbooks	2025-10-06 17:05:41 +00:00
pinecone.ts	chore: Regenerate all playbooks	2025-10-06 17:05:41 +00:00
query-logger.ts	chore: Regenerate all playbooks	2025-10-06 17:05:41 +00:00
rag.ts	chore: Regenerate all playbooks	2025-10-06 17:05:41 +00:00
remote-backend.ts	chore: Regenerate all playbooks	2025-10-06 17:05:41 +00:00
text-processor.ts	chore: Regenerate all playbooks	2025-10-06 17:05:41 +00:00
utils.ts	chore: Regenerate all playbooks	2025-10-06 17:05:41 +00:00