Merge pull request #353 from aurelio-labs/james/sr-async-doc-update

fix: docs outdated

Merge pull request #353 from aurelio-labs/james/sr-async-doc-update
ae08fab8 · James Briggs · GitHub · 72ba7ebd · 7e133a99 · ae08fab8
Unverified Commit ae08fab8 authored 8 months ago by James Briggs Committed by GitHub 8 months ago
--- a/docs/indexes/pinecone_async.ipynb
+++ b/docs/indexes/pinecone_async.ipynb
@@ -6,7 +6,7 @@
   "metadata": {},
   "outputs": [],
   "source": [
-    "!pip install -qU \"semantic-router[pinecone]==0.0.47\""
+    "!pip install -qU \"semantic-router[pinecone]==0.0.52\""
   ]
  },
  {
@@ -181,7 +181,7 @@
    "os.environ[\"PINECONE_API_KEY\"] = os.environ.get(\"PINECONE_API_KEY\") or getpass(\n",
    "    \"Enter Pinecone API key: \"\n",
    ")\n",
-    "pc_index = PineconeIndex(dimensions=1536)"
+    "pc_index = PineconeIndex(dimensions=1536, init_async_index=True)"
   ]
  },
  {

 %% Cell type:code id: tags:

 ``` python
-!pip install -qU "semantic-router[pinecone]==0.0.47"
+!pip install -qU "semantic-router[pinecone]==0.0.52"
 ```

 %% Cell type:code id: tags:

 ``` python
 from semantic_router import Route

 # we could use this as a guide for our chatbot to avoid political conversations
 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!",
    ],
 )

 # this could be used as an indicator to our chatbot to switch to a more
 # conversational prompt
 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",
    ],
 )

 # we place both of our decisions together into single list
 routes = [politics, chitchat]
 ```

 %% Cell type:markdown id: tags:

 As of 13 June 2024, two encoders support async functionality:

 * `AzureOpenAIEncoder`
 * `OpenAIEncoder`

 To use either of these encoders in async mode we simply initialize them as we usually would. When we then include them within a `RouteLayer` and run `acall` the route layer will automatically run the encoders in async mode.

 **Azure OpenAI:**

 ```python
 from semantic_router.encoders import AzureOpenAIEncoder

 encoder = AzureOpenAIEncoder(
    api_key="YOUR_AZURE_OPENAI_API_KEY",
    deployment_name="YOUR_DEPLOYMENT_NAME",
    azure_endpoint="YOUR_ENDPOINT",
    api_version="2024-02-01",
    model="text-embedding-3-small",
 )
 ```

 %% Cell type:markdown id: tags:

 **OpenAI:**

 %% Cell type:code id: tags:

 ``` python
 import os
 from getpass import getpass
 from semantic_router.encoders import OpenAIEncoder

 # get at platform.openai.com
 os.environ["OPENAI_API_KEY"] = os.environ.get("OPENAI_API_KEY") or getpass(
    "Enter OpenAI API key: "
 )
 encoder = OpenAIEncoder(name="text-embedding-3-small")
 ```

 %% Cell type:markdown id: tags:

 We can see encoder details, including default `score_threshold` like so:

 %% Cell type:code id: tags:

 ``` python
 encoder
 ```

 %% Output

    OpenAIEncoder(name='text-embedding-3-small', score_threshold=0.3, type='openai', client=<openai.OpenAI object at 0x117d35e50>, async_client=<openai.AsyncOpenAI object at 0x117d47ad0>, dimensions=NOT_GIVEN, token_limit=8192)

 %% Cell type:markdown id: tags:

 We can create embeddings asynchronously via our encoder using the `encoder.acall` method:

 %% Cell type:code id: tags:

 ``` python
 await encoder.acall(docs=["test", "test 2"])
 ```

 %% Output

    [[-0.009877119213342667,
      0.0015331337926909328,
      0.015642808750271797,
      -0.05476367473602295,
      -0.006405937951058149,
      ...],
     [0.012598802335560322,
      -0.0037690235767513514,
      0.025685198605060577,
      -0.08883649855852127,
      0.0013644769787788391,
      ...]]

 %% Cell type:markdown id: tags:

 For our `PineconeIndex` we do the exact same thing, ie we initialize as usual:

 %% Cell type:code id: tags:

 ``` python
 import os
 from semantic_router.index.pinecone import PineconeIndex

 # get at app.pinecone.io
 os.environ["PINECONE_API_KEY"] = os.environ.get("PINECONE_API_KEY") or getpass(
    "Enter Pinecone API key: "
 )
-pc_index = PineconeIndex(dimensions=1536)
+pc_index = PineconeIndex(dimensions=1536, init_async_index=True)
 ```

 %% Cell type:markdown id: tags:

 There are several async methods we can call directly:

 %% Cell type:code id: tags:

 ``` python
 await pc_index._async_list_indexes()
 ```

 %% Output

    {'indexes': []}

 %% Cell type:markdown id: tags:

 But unless we're using the index directly, we don't need to use these. As with the encoder, once we pass the `PineconeIndex` to our route layer, the route layer will call all async methods automatically when we hit the `acall` method.

 %% Cell type:markdown id: tags:

 ## Async RouteLayer

 %% Cell type:markdown id: tags:

 The `RouteLayer` class supports both sync and async operations by default, so we initialize as usual:

 %% Cell type:code id: tags:

 ``` python
 from semantic_router.layer import RouteLayer

 rl = RouteLayer(encoder=encoder, routes=routes, index=pc_index)
 ```

 %% Cell type:markdown id: tags:

 We can check our route layer and index information as usual:

 %% Cell type:code id: tags:

 ``` python
 rl.list_route_names()
 ```

 %% Output

    ['politics', 'chitchat']

 %% Cell type:code id: tags:

 ``` python
 len(rl.index)
 ```

 %% Output

    10

 %% Cell type:markdown id: tags:

 We can also view all of the records for a given route:

 %% Cell type:code id: tags:

 ``` python
 rl.index._get_route_ids(route_name="politics")
 ```

 %% Output

    ['politics#64069085d9d6e98e5a80915f69fabe82bac6c742f801bc305c5001dce88f0d19',
     'politics#af8b76111f260cf44fb34f04fcf82927dcbe08e8f47c30f4d571379c1512fac8',
     'politics#d1bb40236c3d95b9c695bfa86b314b6da4eb87e136699563fccae47fccea23e2',
     'politics#ed0f3dd7bd5dea12e55b1953bcd2c562a5ab19f501f6d5ff8c8927652c3904b8',
     'politics#fc6d15f9e6075e6de82b3fbef6722b64353e4eadc8d663b7312a4ed60c43e6f6']

 %% Cell type:markdown id: tags:

 And now for async vs. sync usage! To call in synchronous mode we simply hit `rl(...)`, to switch to async mode we hit `rl.acall(...)`:

 %% Cell type:code id: tags:

 ``` python
 rl("don't you love politics").name  # SYNC mode
 ```

 %% Output

    'politics'

 %% Cell type:code id: tags:

 ``` python
 out = await rl.acall("don't you love politics?")  # ASYNC mode
 out.name
 ```

 %% Output

    'politics'

 %% Cell type:markdown id: tags:

 Let's try a few more sync and async requests:

 %% Cell type:code id: tags:

 ``` python
 rl("how's the weather today?").name
 ```

 %% Output

    'chitchat'

 %% Cell type:code id: tags:

 ``` python
 out = await rl.acall("how's the weather today?")
 out.name
 ```

 %% Output

    'chitchat'

 %% Cell type:code id: tags:

 ``` python
 rl("I'm interested in learning about llama 2").name
 ```

 %% Cell type:code id: tags:

 ``` python
 out = await rl.acall("I'm interested in learning about llama 2")
 out.name
 ```

 %% Cell type:markdown id: tags:

 We can delete or update routes using the usual synchronous methods:

 %% Cell type:code id: tags:

 ``` python
 len(rl.index)
 ```

 %% Output

    10

 %% Cell type:code id: tags:

 ``` python
 import time

 rl.delete(route_name="chitchat")
 time.sleep(3)
 len(rl.index)
 ```

 %% Output

    5

 %% Cell type:code id: tags:

 ``` python
 out = await rl.acall("how's the weather today?")
 out.name
 ```

 %% Cell type:code id: tags:

 ``` python
 rl.index.get_routes()
 ```

 %% Output

    [('politics', "why don't you tell me about your political opinions"),
     ('politics',
      "don't you just love the presidentdon't you just hate the president"),
     ('politics', "isn't politics the best thing ever"),
     ('politics', "they're going to destroy this country!"),
     ('politics', 'they will save the country!')]

 %% Cell type:code id: tags:

 ``` python
 rl.index.describe()
 ```

 %% Output

    {'type': 'pinecone', 'dimensions': 1536, 'vectors': 5}

 %% Cell type:markdown id: tags:

 ---