Merge pull request #997 from vespa-engine/kkraune-patch-1

fix format and language
vespa-engine · Dec 19, 2024 · 7df4dd1 · 7df4dd1
2 parents 9d8a797 + bdbeca7
commit 7df4dd1
Showing 1 changed file with 7 additions and 7 deletions.
diff --git a/docs/sphinx/source/examples/colbert_standalone_long_context_Vespa-cloud.ipynb b/docs/sphinx/source/examples/colbert_standalone_long_context_Vespa-cloud.ipynb
@@ -20,9 +20,9 @@
                 "\n",
                 "This guide illustrates how to feed multiple passages per Vespa document (long-context)\n",
                 "\n",
-                "- Compress token vectors using binarization compatible with Vespa unpackbits\n",
+                "- Compress token vectors using binarization compatible with Vespa `unpack_bits`\n",
                 "- Use Vespa hex feed format for binary vectors with mixed vespa tensors\n",
-                "- How to query Vespa with the colbert query tensor representation\n",
+                "- How to query Vespa with the ColBERT query tensor representation\n",
                 "\n",
                 "Read more about [Vespa Long-Context ColBERT](https://blog.vespa.ai/announcing-long-context-colbert-in-vespa/).\n",
                 "\n",
@@ -46,7 +46,7 @@
             "id": "17d765d7",
             "metadata": {},
             "source": [
-                "Load a checkpoint with colbert and obtain document and query embeddings\n"
+                "Load a checkpoint with ColBERT and obtain document and query embeddings\n"
             ]
         },
         {
@@ -102,7 +102,7 @@
             "id": "23b2e1f4",
             "metadata": {},
             "source": [
-                "See the shape of the colbert document embeddings:"
+                "See the shape of the ColBERT document embeddings:"
             ]
         },
         {
@@ -155,7 +155,7 @@
             "source": [
                 "The query is always padded to 32 so in the above we have 32 query token vectors.\n",
                 "\n",
-                "Routines for binarization and output in Vespa tensor format that can be used in queries and in JSON feed.\n"
+                "Routines for binarization and output in Vespa tensor format that can be used in queries and JSON feed.\n"
             ]
         },
         {
@@ -172,7 +172,7 @@
                 "\n",
                 "\n",
                 "def binarize_token_vectors_hex(vectors: torch.Tensor) -> Dict[str, str]:\n",
-                "    # Notice axix=2 to pack the bits in the last dimension which is the token level vectors\n",
+                "    # Notice axix=2 to pack the bits in the last dimension, which is the token level vectors\n",
                 "    binarized_token_vectors = np.packbits(np.where(vectors > 0, 1, 0), axis=2).astype(\n",
                 "        np.int8\n",
                 "    )\n",
@@ -440,7 +440,7 @@
             "id": "cebada8d",
             "metadata": {},
             "source": [
-                "### Querying Vespa with colbert tensors \n"
+                "### Querying Vespa with ColBERT tensors \n"
             ]
         },
         {