hf2vespa 0.1.1__py3-none-any.whl → 0.1.2__py3-none-any.whl

hf2vespa/cli.py

@@ -287,20 +287,26 @@ def feed(
 
     Examples:
 
-        # Basic usage
-        $ hf2vespa feed glue --split test --config ax
+        # Basic streaming
+        hf2vespa feed mteb/msmarco-v2 --config corpus --split corpus --limit 10
 
-        # Filter columns
-        $ hf2vespa feed glue --split test --config ax --include premise --include hypothesis
+        # Rename columns
+        hf2vespa feed mteb/msmarco-v2 --config corpus --split corpus --rename _id:id --limit 5
+
+        # Filter specific columns
+        hf2vespa feed mteb/msmarco-v2 --config corpus --split corpus --include title --include text --limit 5
 
         # Custom namespace and doctype
-        $ hf2vespa feed squad --namespace wiki --doctype article
+        hf2vespa feed mteb/msmarco-v2 --config corpus --split corpus --namespace search --doctype passage --limit 10
+
+        # Use config file for complex mappings
+        hf2vespa feed mteb/msmarco-v2 --config corpus --split corpus --config-file vespa-config.yaml --limit 10
 
-        # Use config file
-        $ hf2vespa feed glue --config ax --config-file mappings.yaml
+        # Skip errors instead of failing
+        hf2vespa feed mteb/msmarco-v2 --config corpus --split corpus --on-error skip --limit 10
 
-        # Preview first 10 records
-        $ hf2vespa feed squad --limit 10
+        # Pipe directly to Vespa
+        hf2vespa feed mteb/msmarco-v2 --config corpus --split corpus --limit 1000 | vespa feed -
     """
     feed_impl(
         dataset=dataset,
@@ -343,14 +349,14 @@ def init(
 
     Examples:
 
-        # Generate config for a dataset
-        $ hf2vespa init glue --config ax
+        # Generate config for MS MARCO corpus
+        hf2vespa init mteb/msmarco-v2 --config corpus -o msmarco-config.yaml
 
         # Specify output file
-        $ hf2vespa init squad --output my-config.yaml
+        hf2vespa init mteb/msmarco-v2 --config corpus --output my-config.yaml
 
-        # Inspect a specific split
-        $ hf2vespa init my-dataset --split validation
+        # Generate config for Cohere embeddings dataset
+        hf2vespa init Cohere/wikipedia-2023-11-embed-multilingual-v3 --config en -o cohere-config.yaml
     """
     from hf2vespa.init import init_command
 
@@ -370,11 +376,18 @@ def install_completion(
 
     Detects your shell automatically, or specify explicitly.
 
+    After installation, restart your shell or source your shell config file
+    (e.g., source ~/.bashrc).
+
     Examples:
 
-        hf2vespa install-completion        # Auto-detect shell
-        hf2vespa install-completion bash   # Explicit bash
-        hf2vespa install-completion zsh    # Explicit zsh
+        # Auto-detect shell
+        hf2vespa install-completion
+
+        # Explicit shell
+        hf2vespa install-completion bash
+        hf2vespa install-completion zsh
+        hf2vespa install-completion fish
     """
     from typer._completion_shared import Shells, install
 

{hf2vespa-0.1.1.dist-info → hf2vespa-0.1.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hf2vespa
-Version: 0.1.1
+Version: 0.1.2
 Summary: Stream HuggingFace datasets to Vespa JSON format
 Author-email: Thomas Thoresen <thomas.h.thoresen@gmail.com>
 License: Apache-2.0

{hf2vespa-0.1.1.dist-info → hf2vespa-0.1.2.dist-info}/RECORD

@@ -1,14 +1,14 @@
 hf2vespa/__init__.py,sha256=kUR5RAFc7HCeiqdlX36dZOHkUI5wI6V_43RpEcD8b-0,22
 hf2vespa/__main__.py,sha256=8swxmM2GAunJQ2Qs91RDMvu28RxSGTiDwuMpgKy4plQ,67
-hf2vespa/cli.py,sha256=SHJErdyixpwKFPuKnGRMwAhWnZdcpwtLlroi2gzPNKU,16258
+hf2vespa/cli.py,sha256=wtyTdYlxn8UyZ7OufB6wJ3tyW73fBDVGecNxat1WhKc,17018
 hf2vespa/config.py,sha256=JmUxnQcEm_XGg4llbAkQnt28HYgWeh2ldyEsk7ZVgMU,3686
 hf2vespa/converters.py,sha256=sLzOQolvUez2ZymOGS3asiGFDDgqns8chpcoIzMkfME,20685
 hf2vespa/init.py,sha256=CF4p9LMLCbwV_OehTsu036p8vjtWK8TngXU9fd_v7SM,10866
 hf2vespa/pipeline.py,sha256=7q9NIF6GhbgcBXx2Jckxh0tcXi7rMJmjcwkXFiPi_tQ,7145
 hf2vespa/stats.py,sha256=1Os61QpIpDJKthXWE5oWmK_SHx4bZUkcgVIK6t16ppk,1944
 hf2vespa/utils.py,sha256=KGV-YwKaO6IPtEpb9NnRrHMxfBOMfjZzrtYJJSUCe14,1706
-hf2vespa-0.1.1.dist-info/METADATA,sha256=5S4Tv0Na0uAGpoWlWSCE7RtedyGQc_13Fci7jIPuFug,23169
-hf2vespa-0.1.1.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-hf2vespa-0.1.1.dist-info/entry_points.txt,sha256=R-1FE95nsxKVDqMWPPcXIQT0FL6J4ZWE-Sri68retXE,46
-hf2vespa-0.1.1.dist-info/top_level.txt,sha256=Xul9tbYYe1Qw2uYuf-tQiPaPdWRPYsH6K3F2LO6X_lI,9
-hf2vespa-0.1.1.dist-info/RECORD,,
+hf2vespa-0.1.2.dist-info/METADATA,sha256=VvjQOSoMorGuIV5gEtob_syvkLfIeBYGWxCauNMsWK4,23169
+hf2vespa-0.1.2.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+hf2vespa-0.1.2.dist-info/entry_points.txt,sha256=R-1FE95nsxKVDqMWPPcXIQT0FL6J4ZWE-Sri68retXE,46
+hf2vespa-0.1.2.dist-info/top_level.txt,sha256=Xul9tbYYe1Qw2uYuf-tQiPaPdWRPYsH6K3F2LO6X_lI,9
+hf2vespa-0.1.2.dist-info/RECORD,,