Correct the usage snippet: load_adapter takes a local directory and returns (encoder, metadata); encode_batch for lists

README.md

@@ -67,26 +67,45 @@ and no difference between them may be read as the cost of anything.
 
 ## Using it
 
+Install the package, then download the adapter and load it from the local directory:
+
+```bash
+pip install 'quanfire-multilingual-embedding[neural]'
+hf download quanfire-ai/embed-eulaw-multi --revision v1.0.0 --local-dir embed-eulaw-multi
+```
+
 ```python
 from multilingual_embedding.embedding.neural.adapter import load_adapter
 
-encoder = load_adapter("quanfire-ai/embed-eulaw-multi")
-vectors = encoder.encode(["Article 5 of Regulation (EU) 2016/679 ..."])
+encoder, meta = load_adapter("embed-eulaw-multi")
+
+texts = [
+    "The processing of personal data shall be lawful only if the data subject has given consent.",
+    "Die Verarbeitung personenbezogener Daten ist nur rechtmaessig, wenn die betroffene Person ihre Einwilligung erteilt hat.",
+    "Member States shall ensure that fishing vessels exceeding 12 metres carry a satellite tracking device.",
+]
+vectors = encoder.encode_batch(texts)
 ```
 
-Install with `pip install multilingual-embedding`.
+`load_adapter` returns the encoder together with its metadata, because the metadata carries
+the prefixes needed to use the model correctly. `encode_batch` takes a list of strings;
+`encode` takes a single string.
+
+On the three sentences above, the English and German expressions of the same provision sit at
+cosine 0.835, while the unrelated fisheries article sits at 0.379.
 
 ### Base revision
 
-This adapter's manifest predates our base pinning convention, so it reads back as unpinned.
-The base revision it was built against is
+This adapter's manifest predates our base pinning convention, so `meta.checkpoint_revision`
+reads back as `None`. The base revision it was built against is
 `614241f622f53c4eeff9890bdc4f31cfecc418b3`, which we establish from the training host's model
-cache rather than from a field the run recorded: that snapshot is the only one present and it
-predates the run by a month. Pin it explicitly if you need byte-stable behaviour:
+cache rather than from a field the run recorded: that snapshot is the only one present there
+and it predates the run by a month. Pass it explicitly if you need the base held still, since
+an upstream repository can change what sits behind a name:
 
 ```python
-encoder = load_adapter(
-    "quanfire-ai/embed-eulaw-multi",
+encoder, meta = load_adapter(
+    "embed-eulaw-multi",
     revision="614241f622f53c4eeff9890bdc4f31cfecc418b3",
 )
 ```