CU-8699j8t08 Update install targets and adapt library changes (#9)

* CU-8699j8t08: Fix minor README issue (technically unrelated)

* CU-8699j8t08: Update install instructions with monorepo release targets

* CU-8699j8t08: Update install targets to monorepo in tutorials

* CU-8699j8t08: Simplfiy install targets

* CU-8699j8t08: Remove accidentally added optional install parts

* CU-8699j8t08: Update some tutorials code to reflect library changes

* Update NER component example code to changes

* Fix arguments for creating a new component

* CU-8699j8t08: Fix typo

* CU-8699j8t08: Update tokenizer registration

* CU-8699j8t08: Fix another typo

* Fix NER component registration in tutorials

Author: mart-r

medcat-v2-tutorials/notebooks/advanced/1._Creating_and_using_a_custom_tokenizer.ipynb

@@ -316,7 +316,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -355,14 +355,9 @@
     "    def get_entity_class(self) -> type[MutableEntity]:\n",
     "        return Entity\n",
     "\n",
-    "    # for creation of class based on config\n",
-    "    @classmethod\n",
-    "    def get_init_args(cls, config: Config) -> list[Any]:\n",
-    "        return []\n",
-    "\n",
     "    @classmethod\n",
-    "    def get_init_kwargs(cls, config: Config) -> dict[str, Any]:\n",
-    "        return {}"
+    "    def create_new_tokenizer(cls, config: Config) -> 'WhitespaceTokenizer':\n",
+    "        return cls()"
    ]
   },
   {
@@ -389,7 +384,7 @@
    ],
    "source": [
     "from medcat.tokenizing.tokenizers import register_tokenizer, list_available_tokenizers\n",
-    "register_tokenizer(\"whitespace-tokenizer\", WhitespaceTokenizer)\n",
+    "register_tokenizer(\"whitespace-tokenizer\", WhitespaceTokenizer.create_new_tokenizer)\n",
     "print(\"Registered tokenizers:\", list_available_tokenizers())"
    ]
   },
@@ -417,7 +412,9 @@
    ],
    "source": [
     "from medcat.tokenizing.tokenizers import create_tokenizer\n",
-    "tokenizer = create_tokenizer(\"whitespace-tokenizer\")\n",
+    "cnf = Config()\n",
+    "cnf.general.nlp.provider = \"whitespace-tokenizer\" \n",
+    "tokenizer = create_tokenizer(\"whitespace-tokenizer\", cnf)\n",
     "print(\"We've got one:\", tokenizer)"
    ]
   },

medcat-v2-tutorials/notebooks/advanced/2._Create_and_use_component.ipynb

@@ -36,6 +36,7 @@
     "from medcat.tokenizing.tokenizers import BaseTokenizer\n",
     "from medcat.vocab import Vocab\n",
     "from medcat.cdb.cdb import CDB\n",
+    "from medcat.config.config import Ner\n",
     "# for the component itself\n",
     "from medcat.components.types import AbstractCoreComponent, CoreComponentType\n",
     "from medcat.tokenizing.tokens import MutableDocument, MutableEntity\n",
@@ -63,11 +64,11 @@
     "    name = \"RANDOM_NER\"\n",
     "\n",
     "    # NOTE: NEED TO IMPLEMENT \n",
-    "    # the arguments provide to the init method in order\n",
     "    @classmethod\n",
-    "    def get_init_args(cls, tokenizer: BaseTokenizer, cdb: CDB, vocab: Vocab,\n",
-    "                      model_load_path: Optional[str]) -> list[Any]:\n",
-    "        return [tokenizer, cdb]\n",
+    "    def create_new_component(\n",
+    "            cls, cnf: Ner, tokenizer: BaseTokenizer, cdb: CDB, vocab: Vocab,\n",
+    "            model_load_path: Optional[str]) -> 'RandomNER':\n",
+    "        return cls(tokenizer, cdb)\n",
     "\n",
     "    # NOTE: NEED TO IMPLEMENT\n",
     "    # the keyword arguments to the init method\n",
@@ -148,7 +149,7 @@
    "outputs": [],
    "source": [
     "from medcat.components.types import register_core_component\n",
-    "register_core_component(CoreComponentType.ner, RandomNER.name, RandomNER)"
+    "register_core_component(CoreComponentType.ner, RandomNER.name, RandomNER.create_new_component)"
    ]
   },
   {

medcat-v2-tutorials/notebooks/introductory/meta/1._Add_a_MetaCat_to_a_Model.ipynb

@@ -76,7 +76,7 @@
     }
    ],
    "source": [
-    "! pip install \"medcat[meta-cat] @ git+https://github.com/CogStack/MedCAT2@v0.8.0\" # NOTE: VERSION-STRING"
+    "! pip install \"medcat[meta-cat] @ git+https://github.com/CogStack/cogstack-nlp@medcat/v0.10.0#subdirectory=medcat-v2\" # NOTE: VERSION-STRING"
    ]
   },
   {

medcat-v2-tutorials/notebooks/introductory/migration/1._Migrate_v1_model_to_v2.ipynb

@@ -131,7 +131,7 @@
     }
    ],
    "source": [
-    "! pip install \"medcat[meta-cat,spacy,deid] @ git+https://github.com/CogStack/MedCAT2@v0.8.0\""
+    "! pip install \"medcat[meta-cat,spacy,deid] @ git+https://github.com/CogStack/cogstack-nlp@medcat/v0.10.0#subdirectory=medcat-v2\""
    ]
   },
   {

medcat-v2-tutorials/requirements.txt

@@ -1,4 +1,4 @@
-medcat @ git+https://github.com/CogStack/MedCAT2@v0.8.0
+medcat @ git+https://github.com/CogStack/cogstack-nlp@medcat/v0.10.0#subdirectory=medcat-v2
 ipykernel
 pytest-xdist~=3.6.0
 nbmake<1.6

medcat-v2/README.md

@@ -45,17 +45,17 @@ Currently MedCAT v2 is in Beta.
 As such, we're not yet pushing to PyPI.
 And because of that the current installation command for (only) core MedCAT v2 is:
 ```
-pip install "medcat @ git+https://github.com/CogStack/MedCAT2@v0.8.0"
+pip install "medcat @ git+https://github.com/CogStack/cogstack-nlp.git@refs/tags/medcat/v0.10.0#subdirectory=medcat-v2"
 ```
 Do note that **this installs only the core MedCAT v2**.
 **It does not necessary dependencies for `spacy`-based tokenizing or MetaCATs or DeID**.
 However, all of those are supported as well.
 You can install them as follows:
 ```
-pip install "medcat[spacy] @ git+https://github.com/CogStack/MedCAT2@v0.8.0"  # for spacy-based tokenizer
-pip install "medcat[meta-cat] @ git+https://github.com/CogStack/MedCAT2@v0.8.0"  # for MetaCAT
-pip install "medcat[deid] @ git+https://github.com/CogStack/MedCAT2@v0.8.0"  # for DeID models
-pip install "medcat[spacy,meta-cat,deid,rel-cat,dict-ner] @ git+https://github.com/CogStack/MedCAT2@v0.8.0"  # for all of the sbove
+pip install "medcat[spacy] @ git+https://github.com/CogStack/cogstack-nlp.git@refs/tags/medcat/v0.10.0#subdirectory=medcat-v2"  # for spacy-based tokenizer
+pip install "medcat[meta-cat] @ git+https://github.com/CogStack/cogstack-nlp.git@refs/tags/medcat/v0.10.0#subdirectory=medcat-v2"  # for MetaCAT
+pip install "medcat[deid] @ git+https://github.com/CogStack/cogstack-nlp.git@refs/tags/medcat/v0.10.0#subdirectory=medcat-v2"  # for DeID models
+pip install "medcat[spacy,meta-cat,deid,rel-cat,dict-ner] @ git+https://github.com/CogStack/cogstack-nlp.git@refs/tags/medcat/v0.10.0#subdirectory=medcat-v2"  # for all of the sbove
 ```
 
 PS: