We typicaly do this through Hetzner, but EC2 or Compute Instances on GCP would also be ok. However, Hetzner is preferred unless you have a strong preference against it.
The preferred region is US-West.
For operating system, pick Ubuntu.
| { | |
| "params": { | |
| "vectors": { | |
| "1024_vectors": { | |
| "size": 1024, | |
| "distance": "Cosine", | |
| "hnsw_config": { | |
| "on_disk": false | |
| }, | |
| "quantization_config": { |
| git branch | grep -v main | xargs git branch -D |
| const createDatasetPayload = JSON.parse("{\"dataset_name\":\"test14\",\"organization_id\":\"95b7c53e-2c24-49a1-97fa-c87188c7324b\",\"server_configuration\":{\"LLM_BASE_URL\":\"\",\"LLM_DEFAULT_MODEL\":\"\",\"EMBEDDING_BASE_URL\":\"https://embedding.trieve.ai\",\"EMBEDDING_MODEL_NAME\":\"jina-base-en\",\"MESSAGE_TO_QUERY_PROMPT\":\"\",\"RAG_PROMPT\":\"\",\"EMBEDDING_SIZE\":768,\"N_RETRIEVALS_TO_INCLUDE\":8,\"DUPLICATE_DISTANCE_THRESHOLD\":1.1,\"DOCUMENT_UPLOAD_FEATURE\":true,\"DOCUMENT_DOWNLOAD_FEATURE\":true,\"COLLISIONS_ENABLED\":false,\"FULLTEXT_ENABLED\":true,\"QDRANT_COLLECTION_NAME\":null,\"EMBEDDING_QUERY_PREFIX\":\"Search for: \",\"USE_MESSAGE_TO_QUERY_PROMPT\":false,\"FREQUENCY_PENALTY\":null,\"TEMPERATURE\":null,\"PRESENCE_PENALTY\":null,\"STOP_TOKENS\":null,\"INDEXED_ONLY\":false,\"LOCKED\":false},\"client_configuration\":\"{}\"}"); | |
| for (let i = 0; i<500; i++) { | |
| createDatasetPayload.dataset_name = `test_${i}`; | |
| fetch("http://localhost:8090/api/dataset", { | |
| "headers": { | |
| "accept": |
| I need to upload image in comment |
| // TODO: latency optimize this so it can be uncommented | |
| if phrases.is_empty() { | |
| let potential_query_split_whitespace = potential_query.split_whitespace().collect_vec(); | |
| if potential_query_split_whitespace.len() > 5 { | |
| continue; | |
| } | |
| let query_without_stop_words = potential_query | |
| .split_whitespace() | |
| .filter(|word| !stop_words.contains(&word.to_lowercase())) | |
| .collect::<Vec<&str>>(); |
| foo.bar.com { | |
| root * /home/git_projects/trieve-hn-discovery/frontend/dist | |
| try_files {path} {path}/ /index.html | |
| file_server | |
| } |
| redis = { version = "0.25", features = [ | |
| "tokio-rustls-comp", | |
| "aio", | |
| "connection-manager", | |
| ] } | |
| actix-extensible-rate-limit = { version = "0.3.1", features = ["redis"] } |
| publishDate | author | title | excerpt | image | category | tags | |
|---|---|---|---|---|---|---|---|
2024-08-12 08:45:00 UTC |
skeptrune (Nick K) |
History of HackerNews Search: From 2007 to 2024 |
The history of HackerNews (HN) search spans three generations. Starting in 2007 with Disqus founder Jason Yan followed by a series of other sites, Octopart/ThriftDB-powered HNSearch in 2011, and finally Algolia-powered search from 2014 to today. |
History |
|
| curl -fsSL https://get.docker.com -o get-docker.sh | |
| sudo sh get-docker.sh |