Find answers from the community

Updated 2 months ago

Difficulty in retrieving documents from

Difficulty in retrieving documents from a word...
v
5 comments
I've ingested the Federalist Papers, as sentences, yet I am unable to retrieve the most relevant document when querying for a single token like "pardons"

Any insights?
Qdrant config (vectors_count: 5674)

Plain Text
{
  "params": {
    "vectors": {
      "size": 768,
      "distance": "Cosine"
    },
    "shard_number": 1,
    "replication_factor": 1,
    "write_consistency_factor": 1,
    "on_disk_payload": true
  },
  "hnsw_config": {
    "m": 16,
    "ef_construct": 100,
    "full_scan_threshold": 10000,
    "max_indexing_threads": 0,
    "on_disk": false
  },
  "optimizer_config": {
    "deleted_threshold": 0.2,
    "vacuum_min_vector_number": 1000,
    "default_segment_number": 0,
    "max_segment_size": null,
    "memmap_threshold": null,
    "indexing_threshold": 20000,
    "flush_interval_sec": 5,
    "max_optimization_threads": null
  },
  "wal_config": {
    "wal_capacity_mb": 32,
    "wal_segments_ahead": 0
  },
  "quantization_config": null
}
Is the Qdrant "vector": null the issue here?
It does appear to have a "Default Vector" in Qdrant UI
ok, this was totally about the embedding model
Add a reply
Sign up and join the conversation on Discord