Lint

0cef1bde · Luca Mannini · 2d3ec8b5 · 0cef1bde · 0cef1bde
Commit 0cef1bde authored 1 year ago by Luca Mannini
--- a/docs/00-introduction.ipynb
+++ b/docs/00-introduction.ipynb
@@ -199,7 +199,6 @@
   "metadata": {},
   "outputs": [],
   "source": [
-    "\n",
    "rl.retrieve_multiple_routes(\"Hi! How are you doing in politics??\")"
   ]
  },

 %% Cell type:markdown id: tags:
 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/aurelio-labs/semantic-router/blob/main/docs/00-introduction.ipynb) [![Open nbviewer](https://raw.githubusercontent.com/pinecone-io/examples/master/assets/nbviewer-shield.svg)](https://nbviewer.org/github/aurelio-labs/semantic-router/blob/main/docs/00-introduction.ipynb)
 %% Cell type:markdown id: tags:
 # Semantic Router Intro
 %% Cell type:markdown id: tags:
 The Semantic Router library can be used as a super fast route making layer on top of LLMs. That means rather than waiting on a slow agent to decide what to do, we can use the magic of semantic vector space to make routes. Cutting route making time down from seconds to milliseconds.
 %% Cell type:markdown id: tags:
 ## Getting Started
 %% Cell type:markdown id: tags:
 We start by installing the library:
 %% Cell type:code id: tags:
 ``` python
 !pip install -qU semantic-router==0.0.20
 ```
 %% Cell type:markdown id: tags:
 We start by defining a dictionary mapping routes to example phrases that should trigger those routes.
 %% Cell type:code id: tags:
 ``` python
 from semantic_router import Route
 politics = Route(
    name="politics",
    utterances=[
        "isn't politics the best thing ever",
        "why don't you tell me about your political opinions",
        "don't you just love the president",
        "don't you just hate the president",
        "they're going to destroy this country!",
        "they will save the country!",
    ],
 )
 ```
 %% Cell type:markdown id: tags:
 Let's define another for good measure:
 %% Cell type:code id: tags:
 ``` python
 chitchat = Route(
    name="chitchat",
    utterances=[
        "how's the weather today?",
        "how are things going?",
        "lovely weather today",
        "the weather is horrendous",
        "let's go to the chippy",
    ],
 )
 routes = [politics, chitchat]
 ```
 %% Cell type:markdown id: tags:
 Now we initialize our embedding model:
 %% Cell type:code id: tags:
 ``` python
 import os
 from getpass import getpass
 from semantic_router.encoders import CohereEncoder, OpenAIEncoder
 # os.environ["COHERE_API_KEY"] = os.getenv("COHERE_API_KEY") or getpass(
 #     "Enter Cohere API Key: "
 # )
 os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY") or getpass(
    "Enter OpenAI API Key: "
 )
 # encoder = CohereEncoder()
 encoder = OpenAIEncoder()
 ```
 %% Cell type:markdown id: tags:
 Now we define the `RouteLayer`. When called, the route layer will consume text (a query) and output the category (`Route`) it belongs to — to initialize a `RouteLayer` we need our `encoder` model and a list of `routes`.
 %% Cell type:code id: tags:
 ``` python
 from semantic_router.layer import RouteLayer
 rl = RouteLayer(encoder=encoder, routes=routes)
 ```
 %% Cell type:markdown id: tags:
 Now we can test it:
 %% Cell type:code id: tags:
 ``` python
 rl("don't you love politics?")
 ```
 %% Cell type:code id: tags:
 ``` python
 rl("how's the weather today?")
 ```
 %% Cell type:markdown id: tags:
 Both are classified accurately, what if we send a query that is unrelated to our existing `Route` objects?
 %% Cell type:code id: tags:
 ``` python
 rl("I'm interested in learning about llama 2")
 ```
 %% Cell type:markdown id: tags:
 We can also retrieve multiple routes with its associated score:
 %% Cell type:code id: tags:
 ``` python
 rl.retrieve_multiple_routes("Hi! How are you doing in politics??")
 ```
 %% Cell type:markdown id: tags:
 In this case, we return `None` because no matches were identified.

--- a/semantic_router/layer.py
+++ b/semantic_router/layer.py
@@ -257,13 +257,17 @@ class RouteLayer:
        results = self._retrieve(xq=vector_arr)
        # decide most relevant routes
-        categories_with_scores = self._semantic_classify_multiple_routes(results, self.score_threshold)
+        categories_with_scores = self._semantic_classify_multiple_routes(
+            results, self.score_threshold
+        )
        route_choices = []
        for category, score in categories_with_scores:
            route = self.check_for_matching_routes(category)
            if route:
-                route_choice = RouteChoice(name=route.name, similarity_score=score, route=route)
+                route_choice = RouteChoice(
+                    name=route.name, similarity_score=score, route=route
+                )
                route_choices.append(route_choice)
        return route_choices
@@ -401,7 +405,9 @@ class RouteLayer:
            logger.warning("No classification found for semantic classifier.")
            return "", []
-    def _semantic_classify_multiple_routes(self, query_results: List[dict], threshold: float) -> List[Tuple[str, float]]:
+    def _semantic_classify_multiple_routes(
+        self, query_results: List[dict], threshold: float
+    ) -> List[Tuple[str, float]]:
        scores_by_class: Dict[str, List[float]] = {}
        for result in query_results:
            score = result["score"]
@@ -411,7 +417,6 @@ class RouteLayer:
            else:
                scores_by_class[route] = [score]
        # Filter classes based on threshold and find max score for each
        classes_above_threshold = []
        for route, scores in scores_by_class.items():
@@ -420,8 +425,7 @@ class RouteLayer:
                classes_above_threshold.append((route, max_score))
        return classes_above_threshold
    def _pass_threshold(self, scores: List[float], threshold: float) -> bool:
        if scores:
            return max(scores) > threshold
@@ -541,8 +545,8 @@ def threshold_random_search(
 if __name__ == "__main__":
    from semantic_router import Route
-    from semantic_router.layer import RouteLayer
    from semantic_router.encoders import OpenAIEncoder
+    from semantic_router.layer import RouteLayer
    # Define routes with example phrases
    politics = Route(
@@ -577,7 +581,13 @@ if __name__ == "__main__":
    rl = RouteLayer(encoder=encoder, routes=routes)
    # Test the RouteLayer with example queries
-    print(rl.retrieve_multiple_routes("how's the weather today?"))  # Expected to match the chitchat route
+    print(
-    print(rl.retrieve_multiple_routes("don't you love politics?"))  # Expected to match the politics route
+        rl.retrieve_multiple_routes("how's the weather today?")
-    print(rl.retrieve_multiple_routes("I'm interested in learning about llama 2"))  # Expected to return None since it doesn't match any route
+    )  # Expected to match the chitchat route
-    print(rl.retrieve_multiple_routes("Hi! How are you doing in politics??")) 
+    print(
\ No newline at end of file
+        rl.retrieve_multiple_routes("don't you love politics?")
+    )  # Expected to match the politics route
+    print(
+        rl.retrieve_multiple_routes("I'm interested in learning about llama 2")
+    )  # Expected to return None since it doesn't match any route
+    print(rl.retrieve_multiple_routes("Hi! How are you doing in politics??"))