nosible 0.2.3__tar.gz → 0.2.5__tar.gz

{nosible-0.2.3/src/nosible.egg-info → nosible-0.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nosible
-Version: 0.2.3
+Version: 0.2.5
 Summary: Python client for the NOSIBLE Search API
 Home-page: https://github.com/NosibleAI/nosible
 Author: Stuart Reid, Matthew Dicks, Richard Taylor, Gareth Warburton
@@ -172,17 +172,16 @@ with Nosible(
     llm_api_key="sk-...",
     openai_base_url="https://api.openrouter.ai/v1"
 ) as client:
-    results = client.search(
+    results = client.fast_search(
         question="What are the terms of the partnership between Microsoft and OpenAI?",
         n_results=20,
+        language="en",
         publish_start="2020-06-01",
         publish_end="2025-06-30",
-        include_netlocs=["nytimes.com", "techcrunch.com"],
-        exclude_netlocs=["example.com"],
         visited_start="2023-06-01",
         visited_end="2025-06-29",
-        include_languages=["en", "fr"],
-        exclude_languages=["de"],
+        include_netlocs=["nytimes.com", "techcrunch.com"],
+        exclude_netlocs=["example.com"],
         include_companies=["/m/04sv4"],  # Microsoft's GKID
         exclude_companies=["/m/045c7b"]  # Google GKID
     )
@@ -203,7 +202,7 @@ with Nosible(
 ```python
 # Example of using your own expansions
 with Nosible() as nos:
-    results = nos.search(
+    results = nos.fast_search(
         question="How have the Trump tariffs impacted the US economy?",
         expansions=[
             "What are the consequences of Trump's 2018 steel and aluminum tariffs on American manufacturers?",
@@ -232,7 +231,7 @@ Allows you to run multiple searches concurrently and `yields` the results as the
 from nosible import Nosible
 
 with Nosible(nosible_api_key="basic|abcd1234...", llm_api_key="sk-...") as client:
-    for batch in client.searches(
+    for batch in client.fast_searches(
         questions=[
             "What are the terms of the partnership between Microsoft and OpenAI?",
             "What exclusivity or non-compete clauses are included in their partnership?"
@@ -249,7 +248,7 @@ Bulk search enables you to retrieve a large number of results in a single reques
 
 - Use the `bulk_search` method when you need more than 1,000 results for a single query.
 - You can request between **1,000 and 10,000** results per query.
-- All parameters available in the standard `search` method—such as `expansions`, `include_companies`, `include_languages`, and more—are also supported in `bulk_search`.
+- All parameters available in the standard `search` method—such as `expansions`, `include_companies`, and more—are also supported in `bulk_search`.
 - A bulk search for 10,000 results typically completes in about 30 seconds or less.
 
 ```python
@@ -272,11 +271,11 @@ Add two ResultSets together:
 from nosible import Nosible
 
 with Nosible(nosible_api_key="basic|abcd1234...") as client:
-    r1 = client.search(
+    r1 = client.fast_search(
         question="What are the terms of the partnership between Microsoft and OpenAI?",
         n_results=5
     )
-    r2 = client.search(
+    r2 = client.fast_search(
         question="How is research governance and decision-making structured between Google and DeepMind?",
         n_results=5
     )
@@ -300,7 +299,7 @@ with Nosible(nosible_api_key="basic|abcd1234...") as client:
         include_netlocs=["arxiv.org", "bbc.com"],
         certain=True
     )
-    results = client.search(search=search)
+    results = client.fast_search(search=search)
     print([r for r in results])
 ```
 
@@ -317,7 +316,7 @@ This fetches a sentiment score for each search result.
 from nosible import Nosible
 
 with Nosible(nosible_api_key="basic|abcd1234...", llm_api_key="sk-...") as client:
-    results = client.search(
+    results = client.fast_search(
         question="What are the terms of the partnership between Microsoft and OpenAI?",
         n_results=1
     )
@@ -333,29 +332,29 @@ Supported formats for saving and loading:
 from nosible import Nosible, ResultSet
 
 with Nosible(nosible_api_key="basic|abcd1234...") as client:
-    combined = client.search(
-        question="What are the terms of the partnership between Microsoft and OpenAI?",
-        n_results=5
-    ) + client.search(
-        question="How is research governance and decision-making structured between Google and DeepMind?",
-        n_results=5
-    )
-
-    # Save
-    combined.to_csv("all_news.csv")
-    combined.to_json("all_news.json")
-    combined.to_parquet("all_news.parquet")
-    combined.to_arrow("all_news.arrow")
-    combined.to_duckdb("all_news.duckdb", table_name="news")
-    combined.to_ndjson("all_news.ndjson")
-
-    # Load
-    rs_csv    = ResultSet.from_csv("all_news.csv")
-    rs_json   = ResultSet.from_json("all_news.json")
-    rs_parq   = ResultSet.from_parquet("all_news.parquet")
-    rs_arrow  = ResultSet.from_arrow("all_news.arrow")
-    rs_duckdb = ResultSet.from_duckdb("all_news.duckdb")
-    rs_ndjson = ResultSet.from_ndjson("all_news.ndjson")
+  combined = client.fast_search(
+    question="What are the terms of the partnership between Microsoft and OpenAI?",
+    n_results=5
+  ) + client.fast_search(
+    question="How is research governance and decision-making structured between Google and DeepMind?",
+    n_results=5
+  )
+
+  # Save
+  combined.write_csv("all_news.csv")
+  combined.write_json("all_news.json")
+  combined.write_parquet("all_news.parquet")
+  combined.write_ipc("all_news.arrow")
+  combined.write_duckdb("all_news.duckdb", table_name="news")
+  combined.write_ndjson("all_news.ndjson")
+
+  # Load
+  rs_csv = ResultSet.read_csv("all_news.csv")
+  rs_json = ResultSet.read_json("all_news.json")
+  rs_parq = ResultSet.read_parquet("all_news.parquet")
+  rs_arrow = ResultSet.read_ipc("all_news.arrow")
+  rs_duckdb = ResultSet.read_duckdb("all_news.duckdb")
+  rs_ndjson = ResultSet.read_ndjson("all_news.ndjson")
 ```
 
 #### More Examples

{nosible-0.2.3 → nosible-0.2.5}/README.md

@@ -129,17 +129,16 @@ with Nosible(
     llm_api_key="sk-...",
     openai_base_url="https://api.openrouter.ai/v1"
 ) as client:
-    results = client.search(
+    results = client.fast_search(
         question="What are the terms of the partnership between Microsoft and OpenAI?",
         n_results=20,
+        language="en",
         publish_start="2020-06-01",
         publish_end="2025-06-30",
-        include_netlocs=["nytimes.com", "techcrunch.com"],
-        exclude_netlocs=["example.com"],
         visited_start="2023-06-01",
         visited_end="2025-06-29",
-        include_languages=["en", "fr"],
-        exclude_languages=["de"],
+        include_netlocs=["nytimes.com", "techcrunch.com"],
+        exclude_netlocs=["example.com"],
         include_companies=["/m/04sv4"],  # Microsoft's GKID
         exclude_companies=["/m/045c7b"]  # Google GKID
     )
@@ -160,7 +159,7 @@ with Nosible(
 ```python
 # Example of using your own expansions
 with Nosible() as nos:
-    results = nos.search(
+    results = nos.fast_search(
         question="How have the Trump tariffs impacted the US economy?",
         expansions=[
             "What are the consequences of Trump's 2018 steel and aluminum tariffs on American manufacturers?",
@@ -189,7 +188,7 @@ Allows you to run multiple searches concurrently and `yields` the results as the
 from nosible import Nosible
 
 with Nosible(nosible_api_key="basic|abcd1234...", llm_api_key="sk-...") as client:
-    for batch in client.searches(
+    for batch in client.fast_searches(
         questions=[
             "What are the terms of the partnership between Microsoft and OpenAI?",
             "What exclusivity or non-compete clauses are included in their partnership?"
@@ -206,7 +205,7 @@ Bulk search enables you to retrieve a large number of results in a single reques
 
 - Use the `bulk_search` method when you need more than 1,000 results for a single query.
 - You can request between **1,000 and 10,000** results per query.
-- All parameters available in the standard `search` method—such as `expansions`, `include_companies`, `include_languages`, and more—are also supported in `bulk_search`.
+- All parameters available in the standard `search` method—such as `expansions`, `include_companies`, and more—are also supported in `bulk_search`.
 - A bulk search for 10,000 results typically completes in about 30 seconds or less.
 
 ```python
@@ -229,11 +228,11 @@ Add two ResultSets together:
 from nosible import Nosible
 
 with Nosible(nosible_api_key="basic|abcd1234...") as client:
-    r1 = client.search(
+    r1 = client.fast_search(
         question="What are the terms of the partnership between Microsoft and OpenAI?",
         n_results=5
     )
-    r2 = client.search(
+    r2 = client.fast_search(
         question="How is research governance and decision-making structured between Google and DeepMind?",
         n_results=5
     )
@@ -257,7 +256,7 @@ with Nosible(nosible_api_key="basic|abcd1234...") as client:
         include_netlocs=["arxiv.org", "bbc.com"],
         certain=True
     )
-    results = client.search(search=search)
+    results = client.fast_search(search=search)
     print([r for r in results])
 ```
 
@@ -274,7 +273,7 @@ This fetches a sentiment score for each search result.
 from nosible import Nosible
 
 with Nosible(nosible_api_key="basic|abcd1234...", llm_api_key="sk-...") as client:
-    results = client.search(
+    results = client.fast_search(
         question="What are the terms of the partnership between Microsoft and OpenAI?",
         n_results=1
     )
@@ -290,29 +289,29 @@ Supported formats for saving and loading:
 from nosible import Nosible, ResultSet
 
 with Nosible(nosible_api_key="basic|abcd1234...") as client:
-    combined = client.search(
-        question="What are the terms of the partnership between Microsoft and OpenAI?",
-        n_results=5
-    ) + client.search(
-        question="How is research governance and decision-making structured between Google and DeepMind?",
-        n_results=5
-    )
-
-    # Save
-    combined.to_csv("all_news.csv")
-    combined.to_json("all_news.json")
-    combined.to_parquet("all_news.parquet")
-    combined.to_arrow("all_news.arrow")
-    combined.to_duckdb("all_news.duckdb", table_name="news")
-    combined.to_ndjson("all_news.ndjson")
-
-    # Load
-    rs_csv    = ResultSet.from_csv("all_news.csv")
-    rs_json   = ResultSet.from_json("all_news.json")
-    rs_parq   = ResultSet.from_parquet("all_news.parquet")
-    rs_arrow  = ResultSet.from_arrow("all_news.arrow")
-    rs_duckdb = ResultSet.from_duckdb("all_news.duckdb")
-    rs_ndjson = ResultSet.from_ndjson("all_news.ndjson")
+  combined = client.fast_search(
+    question="What are the terms of the partnership between Microsoft and OpenAI?",
+    n_results=5
+  ) + client.fast_search(
+    question="How is research governance and decision-making structured between Google and DeepMind?",
+    n_results=5
+  )
+
+  # Save
+  combined.write_csv("all_news.csv")
+  combined.write_json("all_news.json")
+  combined.write_parquet("all_news.parquet")
+  combined.write_ipc("all_news.arrow")
+  combined.write_duckdb("all_news.duckdb", table_name="news")
+  combined.write_ndjson("all_news.ndjson")
+
+  # Load
+  rs_csv = ResultSet.read_csv("all_news.csv")
+  rs_json = ResultSet.read_json("all_news.json")
+  rs_parq = ResultSet.read_parquet("all_news.parquet")
+  rs_arrow = ResultSet.read_ipc("all_news.arrow")
+  rs_duckdb = ResultSet.read_duckdb("all_news.duckdb")
+  rs_ndjson = ResultSet.read_ndjson("all_news.ndjson")
 ```
 
 #### More Examples

{nosible-0.2.3 → nosible-0.2.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "nosible"
-version = "0.2.3"
+version = "0.2.5"
 description = "Python client for the NOSIBLE Search API"
 readme = { file = "README.md", content-type = "text/markdown" }
 requires-python = ">=3.9"

{nosible-0.2.3 → nosible-0.2.5}/src/nosible/classes/result.py

@@ -10,6 +10,7 @@ if TYPE_CHECKING:
     from nosible.classes.result_set import ResultSet
 else:
     ResultSet = None
+import warnings
 
 
 @dataclass(init=True, repr=True, eq=True, frozen=False)
@@ -39,6 +40,32 @@ class Result:
         The language code of the content (e.g., 'en' for English).
     similarity : float, optional
         Similarity score with respect to a query or reference.
+    brand_safety : str, optional
+        Whether it is safe, sensitive, or unsafe to advertise on this content.
+    language : str, optional
+        Language code to use in search (ISO 639-1 language code).
+    continent : str, optional
+        Continent the results must come from (e.g., "Europe", "Asia").
+    region : str, optional
+        Region or subcontinent the results must come from (e.g., "Southern Africa", "Caribbean").
+    country : str, optional
+        Country the results must come from.
+    sector : str, optional
+        GICS Sector the results must relate to (e.g., "Energy", "Information Technology").
+    industry_group : str, optional
+        GICS Industry group the results must relate to (e.g., "Automobiles & Components", "Insurance").
+    industry : str, optional
+        GICS Industry the results must relate to (e.g., "Consumer Finance", "Passenger Airlines").
+    sub_industry : str, optional
+        GICS Sub-industry classification of the content's subject.
+    iab_tier_1 : str, optional
+        IAB Tier 1 category for the content.
+    iab_tier_2 : str, optional
+        IAB Tier 2 category for the content.
+    iab_tier_3 : str, optional
+        IAB Tier 3 category for the content.
+    iab_tier_4 : str, optional
+        IAB Tier 4 category for the content.
 
     Examples
     --------
@@ -84,6 +111,30 @@ class Result:
     """Similarity score with respect to a query or reference."""
     url_hash: str | None = None
     """A hash of the URL for quick comparisons."""
+    brand_safety: str | None = None
+    """Whether it is safe, sensitive, or unsafe to advertise on this content."""
+    continent: str | None = None
+    """Continent the results must come from (e.g., "Europe", "Asia")."""
+    region: str | None = None
+    """Region or subcontinent the results must come from (e.g., "Southern Africa", "Caribbean")."""
+    country: str | None = None
+    """Country the results must come from."""
+    sector: str | None = None
+    """GICS Sector the results must relate to (e.g., "Energy", "Information Technology")."""
+    industry_group: str | None = None
+    """GICS Industry group the results must relate to (e.g., "Automobiles & Components", "Insurance")."""
+    industry: str | None = None
+    """GICS Industry the results must relate to (e.g., "Consumer Finance", "Passenger Airlines")."""
+    sub_industry: str | None = None
+    """GICS Sub-industry classification of the content's subject."""
+    iab_tier_1: str | None = None
+    """IAB Tier 1 category for the content."""
+    iab_tier_2: str | None = None
+    """IAB Tier 2 category for the content."""
+    iab_tier_3: str | None = None
+    """IAB Tier 3 category for the content."""
+    iab_tier_4: str | None = None
+    """IAB Tier 4 category for the content."""
 
     def __str__(self) -> str:
         """
@@ -332,20 +383,32 @@ class Result:
         n_results: int = 100,
         n_probes: int = 30,
         n_contextify: int = 128,
-        algorithm: str = "hybrid-2",
+        algorithm: str = "hybrid-3",
         publish_start: str = None,
         publish_end: str = None,
-        include_netlocs: list = None,
-        exclude_netlocs: list = None,
         visited_start: str = None,
         visited_end: str = None,
         certain: bool = None,
-        include_languages: list = None,
-        exclude_languages: list = None,
+        include_netlocs: list = None,
+        exclude_netlocs: list = None,
         include_companies: list = None,
         exclude_companies: list = None,
         include_docs: list = None,
         exclude_docs: list = None,
+        brand_safety: str = None,
+        language: str = None,
+        continent: str = None,
+        region: str = None,
+        country: str = None,
+        sector: str = None,
+        industry_group: str = None,
+        industry: str = None,
+        sub_industry: str = None,
+        iab_tier_1: str = None,
+        iab_tier_2: str = None,
+        iab_tier_3: str = None,
+        iab_tier_4: str = None,
+        *args, **kwargs
     ) -> ResultSet:
         """
         Find similar search results based on the content or metadata of this Result.
@@ -381,10 +444,6 @@ class Result:
             List of netlocs (domains) to include in the search. (Max: 50)
         exclude_netlocs : list of str, optional
             List of netlocs (domains) to exclude in the search. (Max: 50)
-        include_languages : list of str, optional
-            Languages to include in the search. (Max: 50, ISO 639-1 language codes).
-        exclude_languages : list of str, optional
-            Language codes to exclude in the search (Max: 50, ISO 639-1 language codes).
         include_companies : list of str, optional
             Google KG IDs of public companies to require (Max: 50).
         exclude_companies : list of str, optional
@@ -393,6 +452,32 @@ class Result:
             URL hashes of docs to include (Max: 50).
         exclude_docs : list of str, optional
             URL hashes of docs to exclude (Max: 50).
+        brand_safety : str, optional
+            Whether it is safe, sensitive, or unsafe to advertise on this content.
+        language : str, optional
+            Language code to use in search (ISO 639-1 language code).
+        continent : str, optional
+            Continent the results must come from (e.g., "Europe", "Asia").
+        region : str, optional
+            Region or subcontinent the results must come from (e.g., "Southern Africa", "Caribbean").
+        country : str, optional
+            Country the results must come from.
+        sector : str, optional
+            GICS Sector the results must relate to (e.g., "Energy", "Information Technology").
+        industry_group : str, optional
+            GICS Industry group the results must relate to (e.g., "Automobiles & Components", "Insurance").
+        industry : str, optional
+            GICS Industry the results must relate to (e.g., "Consumer Finance", "Passenger Airlines").
+        sub_industry : str, optional
+            GICS Sub-industry classification of the content's subject.
+        iab_tier_1 : str, optional
+            IAB Tier 1 category for the content.
+        iab_tier_2 : str, optional
+            IAB Tier 2 category for the content.
+        iab_tier_3 : str, optional
+            IAB Tier 3 category for the content.
+        iab_tier_4 : str, optional
+            IAB Tier 4 category for the content.
 
         Returns
         -------
@@ -413,6 +498,17 @@ class Result:
         ...     result = Result(url="https://example.com", title="Example Domain")  # doctest: +SKIP
         ...     similar_results = result.similar(client=nos)  # doctest: +SKIP
         """
+        if "include_languages" in kwargs:
+            warnings.warn(
+                "The 'include_languages' parameter is deprecated and will be removed in a future release. "
+                "Please use the parameter 'language' instead.",
+            )
+        if "exclude_languages" in kwargs:
+            warnings.warn(
+                "The 'exclude_languages' parameter is deprecated and will be removed in a future release. "
+                "Please use the parameter 'language' instead.",
+            )
+
         if client is None:
             raise ValueError("A Nosible client instance must be provided as 'client'.")
         if not self.url:
@@ -436,14 +532,25 @@ class Result:
                 visited_start=visited_start,
                 visited_end=visited_end,
                 certain=certain,
-                include_languages=include_languages,
-                exclude_languages=exclude_languages,
                 include_companies=include_companies,
                 exclude_companies=exclude_companies,
                 include_docs=include_docs,
                 exclude_docs=exclude_docs,
+                brand_safety=brand_safety,
+                language=language,
+                continent=continent,
+                region=region,
+                country=country,
+                sector=sector,
+                industry_group=industry_group,
+                industry=industry,
+                sub_industry=sub_industry,
+                iab_tier_1=iab_tier_1,
+                iab_tier_2=iab_tier_2,
+                iab_tier_3=iab_tier_3,
+                iab_tier_4=iab_tier_4,
             )
-            return client.search(search=s)
+            return client.fast_search(search=s)
         except Exception as e:
             raise RuntimeError(f"Failed to find similar results for title '{self.title}': {e}") from e