Merge branch 'master' of https://github.com/explosion/spaCy

requirements.txt

@@ -10,7 +10,7 @@ six
 html5lib==1.0b8
 ujson>=1.35
 dill>=0.2,<0.3
-requests>=2.13.0,<3.0.0
+requests>=2.11.0,<3.0.0
 regex==2017.4.5
 ftfy>=4.4.2,<5.0.0
 pytest>=3.0.6,<4.0.0

website/docs/api/annotation.jade

@@ -39,7 +39,7 @@ p
 +h(2, "pos-tagging") Part-of-speech Tagging
 
 +infobox("Tip: Understanding tags")
-    |  In spaCy v1.8.3+, you can also use #[code spacy.explain()] to get the
+    |  In spaCy v1.9+, you can also use #[code spacy.explain()] to get the
     |  description for the string representation of a tag. For example,
     |  #[code spacy.explain("RB")] will return "adverb".
 
@@ -71,7 +71,7 @@ p
 +h(2, "dependency-parsing") Syntactic Dependency Parsing
 
 +infobox("Tip: Understanding labels")
-    |  In spaCy v1.8.3+, you can also use #[code spacy.explain()] to get the
+    |  In spaCy v1.9+, you can also use #[code spacy.explain()] to get the
     |  description for the string representation of a label. For example,
     |  #[code spacy.explain("prt")] will return "particle".
 
@@ -80,7 +80,7 @@ include _annotation/_dep-labels
 +h(2, "named-entities") Named Entity Recognition
 
 +infobox("Tip: Understanding entity types")
-    |  In spaCy v1.8.3+, you can also use #[code spacy.explain()] to get the
+    |  In spaCy v1.9+, you can also use #[code spacy.explain()] to get the
     |  description for the string representation of an entity label. For example,
     |  #[code spacy.explain("LANGUAGE")] will return "any named language".
 

website/docs/usage/models.jade

@@ -198,6 +198,37 @@ p
     nlp = en_core_web_md.load()
     doc = nlp(u'This is a sentence.')
 
++h(3, "models-download") Downloading and requiring model dependencies
+
+p
+    |  spaCy's built-in #[+api("cli#download") #[code download]] command
+    |  is mostly intended as a convenient, interactive wrapper. It performs
+    |  compatibility checks and prints detailed error messages and warnings.
+    |  However, if you're downloading models as part of an automated build
+    |  process, this only adds an unecessary layer of complexity. If you know
+    |  which models your application needs, you should be specifying them directly.
+
++aside("Prevent re-downloading models")
+    |  If you're installing a model from a URL, pip will usually re-download and
+    |  re-install the package, even if you already have a matching
+    |  version installed. To prevent this, simply add #[code #egg=] and the
+    |  package name after the URL, e.g. #[code #egg=en_core_web_sm] or
+    |  #[code #egg=en_core_web_sm-1.2.0]. This tells pip which package and version
+    |  you're trying to download, and will skip the package if a matching
+    |  installation is found.
+
+p
+    |  Because all models are valid Python packages, you can add them to your
+    |  application's #[code requirements.txt]. If you're running your own
+    |  internal PyPi installation, you can simply upload the models there. pip's
+    |  #[+a("https://pip.pypa.io/en/latest/reference/pip_install/#requirements-file-format") requirements file format]
+    |  supports both package names to download via a PyPi server, as well as direct
+    |  URLs.
+
++code("requirements.txt", "text").
+    spacy>=1.8.0,<2.0.0
+    -e #{gh("spacy-models")}/releases/download/en_core_web_sm-1.2.0/en_core_web_sm-1.2.0.tar.gz#egg=en_core_web_sm-1.2.0
+
 +h(2, "own-models") Using your own models
 
 p