txt2stix 1.0.1__py3-none-any.whl → 1.0.1.post3__py3-none-any.whl

txt2stix/ai_extractor/__init__.py

@@ -1,4 +1,5 @@
 import logging
+import warnings
 
 import dotenv
 
@@ -12,4 +13,4 @@ for path in ["openai", "anthropic", "gemini", "deepseek", "openrouter"]:
     try:
         __import__(__package__ + "." + path)
     except Exception as e:
-        logging.warning("%s not supported, please install missing modules", path, exc_info=True)
+        pass

txt2stix/extractions.py

@@ -31,8 +31,9 @@ class Extractor(NamedDict):
         self.extraction_key = key
         self.slug = key
         test_cases = test_cases or dict()
-        self.prompt_negative_examples = test_cases.get('test_negative_examples') or []
-        self.prompt_positive_examples = test_cases.get('test_positive_examples') or []
+        
+        self.prompt_negative_examples = remove_empty(test_cases.get('test_negative_examples') or [])
+        self.prompt_positive_examples = remove_empty(test_cases.get('test_positive_examples') or [])
         if self.file and not Path(self.file).is_absolute() and include_path:
             self.file = Path(include_path) / self.file
 
@@ -44,6 +45,9 @@ class Extractor(NamedDict):
             for line in file.read_text().splitlines():
                 self.lookups.add(line.strip())
 
+def remove_empty(iterable: list):
+    return [it for it in iterable if it]
+
 def parse_extraction_config(include_path: Path):
     config = {}
     test_cases = load_test_cases_config(include_path)

txt2stix/txt2stix.py

@@ -38,7 +38,7 @@ def newLogger(name: str) -> logging.Logger:
         level=logging.DEBUG,  # Set the desired logging level
         format=f"%(asctime)s [{name}] [%(levelname)s] %(message)s",
         handlers=[stream_handler],
-        datefmt='%d-%b-%y %H:%M:%S'
+        datefmt='%d-%b-%y %H:%M:%S',
     )
 
     return logging.root
@@ -127,31 +127,122 @@ def parse_bool(value: str):
     value = value.lower()
     return value in ["yes", "y", "true", "1"]
 
+
 def parse_args():
-    EXTRACTORS_PATH = INCLUDES_PATH/"extractions"
+    EXTRACTORS_PATH = INCLUDES_PATH / "extractions"
     all_extractors = extractions.parse_extraction_config(INCLUDES_PATH)
-    
+
     parser = argparse.ArgumentParser(description="File Conversion Tool")
 
-    inf_arg  = parser.add_argument("--input_file", "--input-file", required=True, help="The file to be converted. Must be .txt", type=Path)
-    parser.add_argument("--ai_content_check_provider", required=False, type=parse_model, help="Use an AI model to check wether the content of the file contains threat intelligence. Paticularly useful to weed out vendor marketing.")
-    parser.add_argument("--always_extract", default=True, type=parse_bool, help="Whether to always extract or not depending on output of ai_content_check_provider. Default, extracts even when content_check returns describes_incident=False")
-    name_arg = parser.add_argument("--name", required=True, help="Name of the file, max 124 chars", default="stix-out")
-    parser.add_argument("--created", required=False, default=datetime.now(), help="Allow user to optionally pass --created time in input, which will hardcode the time used in created times")
-    parser.add_argument("--ai_settings_extractions", required=False, type=parse_model, help="(required if AI extraction enabled): passed in format provider:model e.g. openai:gpt4o. Can pass more than one value to get extractions from multiple providers.", metavar="provider[:model]", nargs='+')
-    parser.add_argument("--ai_settings_relationships", required=False, type=parse_model, help="(required if AI relationship enabled): passed in format `provider:model`. Can only pass one model at this time.", metavar="provider[:model]")
+    inf_arg = parser.add_argument(
+        "--input_file",
+        "--input-file",
+        required=True,
+        help="The file to be converted. Must be .txt",
+        type=Path,
+    )
+    parser.add_argument(
+        "--ai_content_check_provider",
+        required=False,
+        type=parse_model,
+        help="Use an AI model to check wether the content of the file contains threat intelligence. Paticularly useful to weed out vendor marketing.",
+    )
+    parser.add_argument(
+        "--ai_extract_if_no_incidence",
+        default=True,
+        type=parse_bool,
+        help="if content check decides the report is not related to cyber security intelligence (e.g. vendor marketing), then you can use this setting to decide wether or not script should proceed. Setting to `false` will stop processing. It is designed to save AI tokens processing unknown content at scale in an automated way.",
+    )
+    name_arg = parser.add_argument(
+        "--name",
+        required=True,
+        help="Name of the file, max 124 chars",
+        default="stix-out",
+    )
+    parser.add_argument(
+        "--created",
+        required=False,
+        default=datetime.now(),
+        help="Allow user to optionally pass --created time in input, which will hardcode the time used in created times",
+    )
+    parser.add_argument(
+        "--ai_settings_extractions",
+        required=False,
+        type=parse_model,
+        help="(required if AI extraction enabled): passed in format provider:model e.g. openai:gpt4o. Can pass more than one value to get extractions from multiple providers.",
+        metavar="provider[:model]",
+        nargs="+",
+    )
+    parser.add_argument(
+        "--ai_settings_relationships",
+        required=False,
+        type=parse_model,
+        help="(required if AI relationship enabled): passed in format `provider:model`. Can only pass one model at this time.",
+        metavar="provider[:model]",
+    )
     parser.add_argument("--labels", type=parse_labels)
-    rmode_arg = parser.add_argument("--relationship_mode", choices=["ai", "standard"], required=True)
-    parser.add_argument("--report_id", type=uuid.UUID, required=False, help="id to use instead of automatically generated `{name}+{created}`", metavar="VALID_UUID")
-    parser.add_argument("--confidence", type=range_type(0,100), default=None, help="value between 0-100. Default if not passed is null.", metavar="[0-100]")
-    parser.add_argument("--tlp_level", "--tlp-level", choices=TLP_LEVEL.levels().keys(), default="clear", help="TLP level, default is clear")
-    extractions_arg = parser.add_argument("--use_extractions", "--use-extractions", default={}, type=functools.partial(parse_extractors_globbed, "extractor", all_extractors),  help="Specify extraction types from the default/local extractions .yaml file", metavar="EXTRACTION1,EXTRACTION2")
-    parser.add_argument("--use_identity", "--use-identity", help="Specify an identity file id (e.g., {\"type\":\"identity\",\"name\":\"demo\",\"identity_class\":\"system\"})", metavar="[stix2 identity json]", type=parse_stix)
-    parser.add_argument("--external_refs", type=parse_ref, help="pass additional `external_references` entry (or entries) to the report object created. e.g --external_ref author=dogesec link=https://dkjjadhdaj.net", default=[], metavar="{source_name}={external_id}", action="extend", nargs='+')
-    parser.add_argument('--ignore_image_refs', default=True, type=parse_bool)
-    parser.add_argument('--ignore_link_refs', default=True, type=parse_bool)
-    parser.add_argument("--ignore_extraction_boundary", default=False, type=parse_bool, help="default if not passed is `false`, but if set to `true` will ignore boundary capture logic for extractions")
-    aflow_arg = parser.add_argument('--ai_create_attack_flow', default=False, action='store_true', help="create attack flow for attack objects in report/bundle")
+    rmode_arg = parser.add_argument(
+        "--relationship_mode", choices=["ai", "standard"], required=True
+    )
+    parser.add_argument(
+        "--report_id",
+        type=uuid.UUID,
+        required=False,
+        help="id to use instead of automatically generated `{name}+{created}`",
+        metavar="VALID_UUID",
+    )
+    parser.add_argument(
+        "--confidence",
+        type=range_type(0, 100),
+        default=None,
+        help="value between 0-100. Default if not passed is null.",
+        metavar="[0-100]",
+    )
+    parser.add_argument(
+        "--tlp_level",
+        "--tlp-level",
+        choices=TLP_LEVEL.levels().keys(),
+        default="clear",
+        help="TLP level, default is clear",
+    )
+    extractions_arg = parser.add_argument(
+        "--use_extractions",
+        "--use-extractions",
+        default={},
+        type=functools.partial(parse_extractors_globbed, "extractor", all_extractors),
+        help="Specify extraction types from the default/local extractions .yaml file",
+        metavar="EXTRACTION1,EXTRACTION2",
+    )
+    parser.add_argument(
+        "--use_identity",
+        "--use-identity",
+        help='Specify an identity file id (e.g., {"type":"identity","name":"demo","identity_class":"system"})',
+        metavar="[stix2 identity json]",
+        type=parse_stix,
+    )
+    parser.add_argument(
+        "--external_refs",
+        type=parse_ref,
+        help="pass additional `external_references` entry (or entries) to the report object created. e.g --external_ref author=dogesec link=https://dkjjadhdaj.net",
+        default=[],
+        metavar="{source_name}={external_id}",
+        action="extend",
+        nargs="+",
+    )
+    parser.add_argument("--ignore_image_refs", default=True, type=parse_bool)
+    parser.add_argument("--ignore_link_refs", default=True, type=parse_bool)
+    parser.add_argument(
+        "--ignore_extraction_boundary",
+        default=False,
+        type=parse_bool,
+        help="default if not passed is `false`, but if set to `true` will ignore boundary capture logic for extractions",
+    )
+    aflow_arg = parser.add_argument(
+        "--ai_create_attack_flow",
+        default=False,
+        action="store_true",
+        help="create attack flow for attack objects in report/bundle",
+    )
 
     args = parser.parse_args()
     if not args.input_file.exists():
@@ -159,18 +250,27 @@ def parse_args():
     if len(args.name) > 124:
         raise argparse.ArgumentError(name_arg, "max 124 characters")
 
-    if args.relationship_mode == 'ai' and not args.ai_settings_relationships:
-        raise argparse.ArgumentError(rmode_arg, "relationship_mode is set to AI, --ai_settings_relationships is required")
+    if args.relationship_mode == "ai" and not args.ai_settings_relationships:
+        raise argparse.ArgumentError(
+            rmode_arg,
+            "relationship_mode is set to AI, --ai_settings_relationships is required",
+        )
 
     if args.ai_create_attack_flow and not args.ai_settings_relationships:
-        raise argparse.ArgumentError(aflow_arg, "--ai_create_attack_flow requires --ai_settings_relationships")
-    #### process --use-extractions 
-    if args.use_extractions.get('ai') and not args.ai_settings_extractions:
-        raise argparse.ArgumentError(extractions_arg, "ai based extractors are passed, --ai_settings_extractions is required")
+        raise argparse.ArgumentError(
+            aflow_arg, "--ai_create_attack_flow requires --ai_settings_relationships"
+        )
+    #### process --use-extractions
+    if args.use_extractions.get("ai") and not args.ai_settings_extractions:
+        raise argparse.ArgumentError(
+            extractions_arg,
+            "ai based extractors are passed, --ai_settings_extractions is required",
+        )
 
-    args.all_extractors  = all_extractors
+    args.all_extractors = all_extractors
     return args
 
+
 REQUIRED_ENV_VARIABLES = [
     "INPUT_TOKEN_LIMIT",
     "CTIBUTLER_BASE_URL",
@@ -243,12 +343,12 @@ def validate_token_count(max_tokens, input, extractors: list[BaseAIExtractor]):
         token_count = _count_token(extractor, input)
         if  token_count > max_tokens:
             raise FatalException(f"{extractor.extractor_name}: input_file token count ({token_count}) exceeds INPUT_TOKEN_LIMIT ({max_tokens})")
-    
+
 
 @functools.lru_cache
 def _count_token(extractor: BaseAIExtractor, input: str):
     return extractor.count_tokens(input)
-        
+
 def run_txt2stix(bundler: txt2stixBundler, preprocessed_text: str, extractors_map: dict,
                 ai_content_check_provider=None,
                 ai_create_attack_flow=None,
@@ -257,7 +357,7 @@ def run_txt2stix(bundler: txt2stixBundler, preprocessed_text: str, extractors_ma
                 ai_settings_relationships=None,
                 relationship_mode="standard",
                 ignore_extraction_boundary=False,
-                always_extract=False, # continue even if ai_content_check fails
+                ai_extract_if_no_incidence=True, # continue even if ai_content_check fails
 
                 **kwargs
         ) -> Txt2StixData:
@@ -276,7 +376,7 @@ def run_txt2stix(bundler: txt2stixBundler, preprocessed_text: str, extractors_ma
             bundler.report.labels.append(f'txt2stix:{classification}'.lower())
         bundler.add_summary(retval.content_check.summary, model.extractor_name)
 
-    if should_extract or always_extract:
+    if should_extract or ai_extract_if_no_incidence:
         if extractors_map.get("ai"):
             validate_token_count(input_token_limit, preprocessed_text, ai_settings_extractions)
         if relationship_mode == "ai":

{txt2stix-1.0.1.dist-info → txt2stix-1.0.1.post3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: txt2stix
-Version: 1.0.1
+Version: 1.0.1.post3
 Summary: txt2stix is a Python script that is designed to identify and extract IoCs and TTPs from text files, identify the relationships between them, convert them to STIX 2.1 objects, and output as a STIX 2.1 bundle.
 Project-URL: Homepage, https://github.com/muchdogesec/txt2stix
 Project-URL: Issues, https://github.com/muchdogesec/txt2stix/issues
@@ -15,11 +15,7 @@ Requires-Python: >=3.9
 Requires-Dist: base58>=2.1.1
 Requires-Dist: beautifulsoup4>=4.12.3
 Requires-Dist: llama-index-core>=0.12.42
-Requires-Dist: llama-index-llms-anthropic>=0.7.2
-Requires-Dist: llama-index-llms-deepseek>=0.1.2
-Requires-Dist: llama-index-llms-gemini>=0.5.0
 Requires-Dist: llama-index-llms-openai>=0.4.5
-Requires-Dist: llama-index-llms-openrouter>=0.3.2
 Requires-Dist: mistune>=3.0.2
 Requires-Dist: pathvalidate>=3.2.0
 Requires-Dist: phonenumbers>=8.13.39
@@ -30,10 +26,19 @@ Requires-Dist: stix2extensions
 Requires-Dist: tld>=0.13
 Requires-Dist: tldextract>=5.1.2
 Requires-Dist: validators>=0.28.3
+Provides-Extra: anthropic
+Requires-Dist: llama-index-llms-anthropic>=0.7.2; extra == 'anthropic'
+Provides-Extra: deepseek
+Requires-Dist: llama-index-llms-deepseek>=0.1.2; extra == 'deepseek'
+Provides-Extra: gemini
+Requires-Dist: llama-index-llms-gemini>=0.5.0; extra == 'gemini'
+Provides-Extra: openrouter
+Requires-Dist: llama-index-llms-openrouter>=0.3.2; extra == 'openrouter'
 Provides-Extra: tests
 Requires-Dist: pytest; extra == 'tests'
 Requires-Dist: pytest-cov; extra == 'tests'
 Requires-Dist: pytest-subtests; extra == 'tests'
+Requires-Dist: python-dateutil; extra == 'tests'
 Requires-Dist: requests; extra == 'tests'
 Description-Content-Type: text/markdown
 
@@ -85,7 +90,13 @@ cd txt2stix
 python3 -m venv txt2stix-venv
 source txt2stix-venv/bin/activate
 # install requirements
-pip3 install .
+pip3 install txt2stix
+```
+
+Note, by default txt2stix will install OpenAI to use as the AI provider. You can also use Anthropic, Gemini, OpenRouter or Deepseek. You need to install these manually if you plan to use them as follows (remove those that don't apply)
+
+```shell
+pip3 install txt2stix[deepseek,gemini,anthropic,openrouter]
 ```
 
 ### Set variables
@@ -113,39 +124,39 @@ The following arguments are available:
 
 #### Input settings
 
-* `--input_file` (REQUIRED): the file to be converted. Must be `.txt`
+* `--input_file` (`path/to/file.txt`, required): the file to be converted. Must be `.txt`
 
 #### STIX Report generation settings
 
 
-* `--name` (REQUIRED): name of file, max 72 chars. Will be used in the STIX Report Object created.
-* `--report_id` (OPTIONAL): Sometimes it is required to control the id of the `report` object generated. You can therefore pass a valid UUIDv4 in this field to be assigned to the report. e.g. passing `2611965-930e-43db-8b95-30a1e119d7e2` would create a STIX object id `report--2611965-930e-43db-8b95-30a1e119d7e2`. If this argument is not passed, the UUID will be randomly generated.
-* `--tlp_level` (OPTIONAL): Options are `clear`, `green`, `amber`, `amber_strict`, `red`. Default if not passed, is `clear`.
-* `--confidence` (OPTIONAL): value between 0-100. Default if not passed is null.
+* `--name` (text, required): name of file, max 72 chars. Will be used in the STIX Report Object created.
+* `--report_id` (UUIDv4, default is random UUIDv4): Sometimes it is required to control the id of the `report` object generated. You can therefore pass a valid UUIDv4 in this field to be assigned to the report. e.g. passing `2611965-930e-43db-8b95-30a1e119d7e2` would create a STIX object id `report--2611965-930e-43db-8b95-30a1e119d7e2`. If this argument is not passed, the UUID will be randomly generated.
+* `--tlp_level` (dictionary, default, `clear`): Options are `clear`, `green`, `amber`, `amber_strict`, `red`.
+* `--confidence` (value between 0-100): If not passed, report will be assigned no confidence score value
 * `--labels` (OPTIONAL): comma seperated list of labels. Case-insensitive (will all be converted to lower-case). Allowed `a-z`, `0-9`. e.g.`label1,label2` would create 2 labels.
-* `--created` (OPTIONAL): by default all object `created` times will take the time the script was run. If you want to explicitly set these times you can do so using this flag. Pass the value in the format `YYYY-MM-DDTHH:MM:SS.sssZ` e.g. `2020-01-01T00:00:00.000Z`
-* `--use_identity` (OPTIONAL): can pass a full STIX 2.1 identity object (make sure to properly escape). Will be validated by the STIX2 library.
+* `--created` (datetime, optional): by default all object `created` times will take the time the script was run. If you want to explicitly set these times you can do so using this flag. Pass the value in the format `YYYY-MM-DDTHH:MM:SS.sssZ` e.g. `2020-01-01T00:00:00.000Z`
+* `--use_identity` (stix identity, optional, default txt2stix identity): can pass a full STIX 2.1 identity object (make sure to properly escape). Will be validated by the STIX2 library.
 * `--external_refs` (OPTIONAL): txt2stix will automatically populate the `external_references` of the report object it creates for the input. You can use this value to add additional objects to `external_references`. Note, you can only add `source_name` and `external_id` values currently. Pass as `source_name=external_id`. e.g. `--external_refs txt2stix=demo1 source=id` would create the following objects under the `external_references` property: `{"source_name":"txt2stix","external_id":"demo1"},{"source_name":"source","external_id":"id"}`
 
 #### Output settings
 
 How the extractions are performed
 
-* `--use_extractions` (REQUIRED): if you only want to use certain extraction types, you can pass their slug found in either `includes/ai/config.yaml`, `includes/lookup/config.yaml` `includes/pattern/config.yaml` (e.g. `pattern_ipv4_address_only`). Default if not passed, no extractions applied. You can also pass a catch all wildcard `*` which will match all extraction paths (e.g. `'pattern_*'` would run all extractions starting with `pattern_` -- make sure to use quotes when using a wildcard)
+* `--use_extractions` (dictionary, required): if you only want to use certain extraction types, you can pass their slug found in either `includes/ai/config.yaml`, `includes/lookup/config.yaml` `includes/pattern/config.yaml` (e.g. `pattern_ipv4_address_only`). Default if not passed, no extractions applied. You can also pass a catch all wildcard `*` which will match all extraction paths (e.g. `'pattern_*'` would run all extractions starting with `pattern_` -- make sure to use quotes when using a wildcard)
 	* Important: if using any AI extractions (`ai_*`), you must set an AI API key in your `.env` file
 	* Important: if you are using any MITRE ATT&CK, CAPEC, CWE, ATLAS or Location extractions you must set `CTIBUTLER` or NVD CPE or CVE extractions you must set `VULMATCH` settings in your `.env` file
-* `--relationship_mode` (REQUIRED): either.
+* `--relationship_mode` (dictionary, required): either.
 	* `ai`: AI provider must be enabled. extractions performed by either regex or AI for extractions user selected. Rich relationships created from AI provider from extractions.
 	* `standard`: extractions performed by either regex or AI (AI provider must be enabled) for extractions user selected. Basic relationships created from extractions back to master Report object generated.
-* `--ignore_extraction_boundary` (OPTIONAL, default `false`, not compatible with AI extractions): in some cases the same string will create multiple extractions depending on extractions set (e.g. `https://www.google.com/file.txt` could create a url, url with file, domain, subdomain, and file). The default behaviour is for txt2stix to take the longest extraction and ignore everything else (e.g. only extract url with file, and ignore url, file, domain, subdomain, and file). If you want to override this behaviour and get all extractions in the output, set this flag to `true`.
-* `--ignore_image_refs` (default `true`): images references in documents don't usually need extracting. e.g. `<img src="https://example.com/image.png" alt="something">` you would not want domain or file extractions extracting `example.com` and `image.png`. Hence these are ignored by default (they are removed from text sent to extraction). Note, only the `img src` is ignored, all other values e.g. `alt` are considered. If you want extractions to consider this data, set it to `false`
-* `--ignore_link_refs` (default `true`): link references in documents don't usually need extracting e.g. `<a href="https://example.com/link.html" title="something">Bad Actor</a>` you would only want `Bad actor` to be considered for extraction. Hence these part of the link are ignored by default (they are removed from text sent to extraction). Note, only the `a href` is ignored, all other values e.g. `title` are considered. Setting this to `false` will also include everything inside the link tag (e.g. `example.com` would extract as a domain)
+* `--ignore_extraction_boundary` (boolean, default `false`, not compatible with AI extractions): in some cases the same string will create multiple extractions depending on extractions set (e.g. `https://www.google.com/file.txt` could create a url, url with file, domain, subdomain, and file). The default behaviour is for txt2stix to take the longest extraction and ignore everything else (e.g. only extract url with file, and ignore url, file, domain, subdomain, and file). If you want to override this behaviour and get all extractions in the output, set this flag to `true`.
+* `--ignore_image_refs` (boolean, default `true`): images references in documents don't usually need extracting. e.g. `<img src="https://example.com/image.png" alt="something">` you would not want domain or file extractions extracting `example.com` and `image.png`. Hence these are ignored by default (they are removed from text sent to extraction). Note, only the `img src` is ignored, all other values e.g. `alt` are considered. If you want extractions to consider this data, set it to `false`
+* `--ignore_link_refs` (boolean, default `true`): link references in documents don't usually need extracting e.g. `<a href="https://example.com/link.html" title="something">Bad Actor</a>` you would only want `Bad actor` to be considered for extraction. Hence these part of the link are ignored by default (they are removed from text sent to extraction). Note, only the `a href` is ignored, all other values e.g. `title` are considered. Setting this to `false` will also include everything inside the link tag (e.g. `example.com` would extract as a domain)
 
 #### AI settings
 
 If any AI extractions, or AI relationship mode is set, you must set the following accordingly
 
-* `--ai_settings_extractions`:
+* `--ai_settings_extractions` (`model:provider`, required if one or more AI extractions set):
 	* defines the `provider:model` to be used for extractions. You can supply more than one provider. Seperate with a space (e.g. `openrouter:openai/gpt-4o` `openrouter:deepseek/deepseek-chat`) If more than one provider passed, txt2stix will take extractions from all models, de-dupelicate them, and them package them in the output. Currently supports:
 		* Provider (env var required `OPENROUTER_API_KEY`): `openrouter:`, providers/models `openai/gpt-4o`, `deepseek/deepseek-chat` ([More here](https://openrouter.ai/models))
 		* Provider (env var required `OPENAI_API_KEY`): `openai:`, models e.g.: `gpt-4o`, `gpt-4o-mini`, `gpt-4-turbo`, `gpt-4` ([More here](https://platform.openai.com/docs/models))
@@ -153,11 +164,15 @@ If any AI extractions, or AI relationship mode is set, you must set the followin
 		* Provider (env var required `GOOGLE_API_KEY`): `gemini:models/`, models: `gemini-1.5-pro-latest`, `gemini-1.5-flash-latest` ([More here](https://ai.google.dev/gemini-api/docs/models/gemini))
 		* Provider (env var required `DEEPSEEK_API_KEY`): `deepseek:`, models `deepseek-chat` ([More here](https://api-docs.deepseek.com/quick_start/pricing))
 	* See `tests/manual-tests/cases-ai-extraction-type.md` for some examples
-* `--ai_settings_relationships`:
+* `--ai_settings_relationships` (`model:provider`, required if AI relationship mode set):
 	* similar to `ai_settings_extractions` but defines the model used to generate relationships. Only one model can be provided. Passed in same format as `ai_settings_extractions`
 	* See `tests/manual-tests/cases-ai-relationships.md` for some examples
-* `--ai_content_check_provider`: Passing this flag will get the AI to try and classify the text in the input to 1) determine if it is talking about threat intelligence, and 2) what type of threat intelligence it is talking about. For context, we use this to filter out non-threat intel posts in Obstracts and Stixify. You pass `provider:model` with this flag to determine the AI model you wish to use to perform the check.
-* `--ai_create_attack_flow`: passing this flag will also prompt the AI model (the same entered for `--ai_settings_relationships`) to generate an [Attack Flow](https://center-for-threat-informed-defense.github.io/attack-flow/) for the MITRE ATT&CK extractions to define the logical order in which they are being described. You must pass `--ai_settings_relationships` for this to work.
+
+#### Other AI related settings
+
+* `--ai_content_check_provider` (`model:provider`, required if passed): Passing this flag will get the AI to try and classify the text in the input to 1) determine if it is talking about threat intelligence, and 2) what type of threat intelligence it is talking about. For context, we use this to filter out non-threat intel posts in Obstracts and Stixify. You pass `provider:model` with this flag to determine the AI model you wish to use to perform the check. It will also create a summary of the content passed (and store this into a STIX Note).
+* `--ai_extract_if_no_incidence` (boolean, default `true`) if content check decides the report is not related to cyber security intelligence (e.g. vendor marketing), then you can use this setting to decide wether or not script should proceed. Setting to `false` will stop processing. It is designed to save AI tokens processing unknown content at scale in an automated way.
+* `--ai_create_attack_flow` (boolean): passing this flag will also prompt the AI model (the same entered for `--ai_settings_relationships`) to generate an [Attack Flow](https://center-for-threat-informed-defense.github.io/attack-flow/) for the MITRE ATT&CK extractions to define the logical order in which they are being described. You must pass `--ai_settings_relationships` for this to work.
 
 ## Adding new extractions
 

{txt2stix-1.0.1.dist-info → txt2stix-1.0.1.post3.dist-info}/RECORD

@@ -2,14 +2,14 @@ txt2stix/__init__.py,sha256=Sm_VT913IFuAZ6dJEdVz3baPwC5VYtHySVfBAOUG92w,803
 txt2stix/attack_flow.py,sha256=WWlukuQYrGW1SJ1DnhfROYC5Ck4WYqNifgmtiuyDg7E,4177
 txt2stix/bundler.py,sha256=EVTcVgZyVMwb6XjNQ3Gyj7zm44UErXo9wbVr2JGsjQQ,16797
 txt2stix/common.py,sha256=ISnGNKqJPE1EcfhL-x_4G18mcwt1urmorkW-ru9kV-0,585
-txt2stix/extractions.py,sha256=ExynKWSeuWOC0q6i4SuU1NkeNw7uoOm6xu0YtJRVaiE,2058
+txt2stix/extractions.py,sha256=_tlsqYHhfAoV-PJzxRHysrX47uxCsMlSg7PQWxww1u0,2171
 txt2stix/indicator.py,sha256=c6S0xx0K8JM-PT_Qd1PlN_ZlDXdnEwiRS8529iUp3yg,30774
 txt2stix/lookups.py,sha256=h42YVtYUkWZm6ZPv2h5hHDHDzDs3yBqrT_T7pj2MDZI,2301
 txt2stix/retriever.py,sha256=zU8L00RSh9N5J0NpAo3CM3IHsuZsNVjJGohRisXcMRs,5167
 txt2stix/stix.py,sha256=9nXD9a2dCY4uaatl-mlIA1k3srwQBhGW-tUSho3iYe0,30
-txt2stix/txt2stix.py,sha256=Vt9CUsSEO1bw5SS7vlsVxktFz1nW8M_G4-RN6idOTA0,16444
+txt2stix/txt2stix.py,sha256=RzGmzkIViEHO45GsxStcz5nbE0ynhifVeJpTalFSlZc,17405
 txt2stix/utils.py,sha256=P66yq-SphsQu2S9At6BfYpavfghXsZqh4h6W13HUEoI,3256
-txt2stix/ai_extractor/__init__.py,sha256=RcXh30ZcIA3Fva2bOPH4EtWq6ffWhGE39C_II8ElAx0,417
+txt2stix/ai_extractor/__init__.py,sha256=5Tf6Co9THzytBdFEVhD-7vvT05TT3nSpltnAV1sfdoM,349
 txt2stix/ai_extractor/anthropic.py,sha256=mdz-8CB-BSCEqnK5l35DRZURVPUf508ef2b48XMxmuk,441
 txt2stix/ai_extractor/base.py,sha256=MAtnKvWUmWZgnzwDM0i2n-WrRWq69du4KVcapNMIsEg,3523
 txt2stix/ai_extractor/deepseek.py,sha256=2XehIYbWXG6Odq68nQX4CNtl5GdmBlAmjLP_lG2eEFo,660
@@ -112,8 +112,8 @@ txt2stix/includes/lookups/threat_actor.txt,sha256=QfDO9maQuqKBgW_Sdd7VGv1SHZ9Ra-
 txt2stix/includes/lookups/tld.txt,sha256=-MEgJea2NMG_KDsnc4BVvI8eRk5Dm93L-t8SGYx5wMo,8598
 txt2stix/includes/lookups/tool.txt,sha256=HGKG6JpUE26w6ezzSxOjBkp15UpSaB7N-mZ_NU_3G7A,6
 txt2stix/includes/tests/test_cases.yaml,sha256=QD1FdIunpPkOpsn6wJRqs2vil_hv8OSVaqUp4a96aZg,22247
-txt2stix-1.0.1.dist-info/METADATA,sha256=rg6DP9idqFjH6eK2FbVmHxCgk-XnQ9mNTbFg3re-dvE,12916
-txt2stix-1.0.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-txt2stix-1.0.1.dist-info/entry_points.txt,sha256=x6QPtt65hWeomw4IpJ_wQUesBl1M4WOLODbhOKyWMFg,55
-txt2stix-1.0.1.dist-info/licenses/LICENSE,sha256=BK8Ppqlc4pdgnNzIxnxde0taoQ1BgicdyqmBvMiNYgY,11364
-txt2stix-1.0.1.dist-info/RECORD,,
+txt2stix-1.0.1.post3.dist-info/METADATA,sha256=6rWnpDd2GTg0rjflOVndvCsbEISnV4rxhRj21as6SqI,14289
+txt2stix-1.0.1.post3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+txt2stix-1.0.1.post3.dist-info/entry_points.txt,sha256=x6QPtt65hWeomw4IpJ_wQUesBl1M4WOLODbhOKyWMFg,55
+txt2stix-1.0.1.post3.dist-info/licenses/LICENSE,sha256=BK8Ppqlc4pdgnNzIxnxde0taoQ1BgicdyqmBvMiNYgY,11364
+txt2stix-1.0.1.post3.dist-info/RECORD,,