stuff not in v2.0.0

Author: Jeadie

evals/README.md

@@ -6,6 +6,7 @@ Spice can be used to both run language models but also to evaluate their perform
 
 This recipe demonstrates how to measure the performance of a language model, configured entirely in the spice runtime.
 
+
 ## Prerequisites
 
 - Ensure you have the Spice CLI installed. Follow the [Getting Started](https://docs.spiceai.org/getting-started) if you haven't done so.
@@ -23,27 +24,12 @@ spice run
 2. Run an evaluation against `my_model`. This will take a moment to complete.
 
 ```shell
-curl -XPOST "http://localhost:8090/v1/evals/tetris" \
-  -H "Content-Type: application/json" \
-  -d '{
-    "model": "my_model"
-  }'
+spice eval tetris --model my_model
 ```
 
-```json
-[
-  {
-    "id": "15b8c5351cff98d96db28b8c76ad19dc",
-    "created_at": "2024-12-30T06:14:54",
-    "dataset": "small_tetris",
-    "model": "my_model",
-    "status": "Completed",
-    "scorers": ["match"],
-    "metrics": {
-      "match/mean": 0.375
-    }
-  }
-]
+```text
+ID                               CREATEDAT           DATASET     MODEL    STATUS    SCORERS METRICS
+15b8c5351cff98d96db28b8c76ad19dc 2024-12-30T06:14:54 small_tetris my_model Completed [match] map[match/mean:0.375]
 ```
 
 3. Inspect the results

mcp/README.md

@@ -126,7 +126,7 @@ ai_chat                                     ✅     15417.63ms 8cda3b72ccc32496
 
 ## Connect to Spice over MCP
 
-Spice is an MCP server. It can be connected to like any other MCP server running over HTTP SSE.
+Spice is an MCP server. It can be connected to like any other MCP server running over HTTP.
 
 1. Clone the cookbook, and navigate to the MCP recipe.
 
@@ -169,7 +169,7 @@ kind: Spicepod
 
 tools:
   - name: spice_mcp
-    from: mcp:http://localhost:8090/v1/mcp/sse
+    from: mcp:http://localhost:8090/v1/mcp
 ```
 
 6. Run the second Spice instance on separate ports.

mcp/child/spicepod.yaml

@@ -4,7 +4,7 @@ kind: Spicepod
 
 tools:
   - name: spice_mcp
-    from: mcp:http://localhost:8090/v1/mcp/sse
+    from: mcp:http://localhost:8090/v1/mcp
 
 models:
   - name: openai-with-spice

websearch/README.md

@@ -11,7 +11,7 @@ This recipe demonstrates how to configure and use Perplexity web search within S
   - `SPICE_PERPLEXITY_AUTH_TOKEN`: A valid authentication token for the Perplexity API. Obtain it from [Perplexity's Getting Started guide](https://docs.perplexity.ai/guides/getting-started).
   - `SPICE_OPENAI_API_KEY`: A valid OpenAI API key (or equivalent).
 
-## Using Perplexity for internet-informed conversations.
+## Using web search for internet-informed conversations
 
 1. Start the Spice runtime:
 
@@ -25,23 +25,9 @@ spice run
 spice chat
 ```
 
-3. Select `perp`
+3. Ask a question
 
 ```shell
-Use the arrow keys to navigate: ↓ ↑ → ←
-? Select model:
-    openai-w-internet
-  ▸ perp
-```
-
-4. Ask a question
-
-```shell
-spice chat
-```
-
-```shell
-Using model: perp
 chat>  What's the weather in Korea this week?
 Here's a summary of the weather in Seoul, South Korea, for this week:
 
@@ -62,7 +48,7 @@ The weather will transition from cold and snowy to clearer conditions by the wee
 Time: 5.02s (first token 1.50s). Tokens: 345. Prompt: 35. Completion: 310 (88.28/s).
 ```
 
-5. Check the citations used by the model
+4. Check the citations used by the model
 
 ```shell
 spice sql
@@ -117,16 +103,7 @@ spice run
 spice chat
 ```
 
-3. Select `openai-w-internet`
-
-```shell
-Use the arrow keys to navigate: ↓ ↑ → ←
-? Select model:
-  ▸ openai-w-internet
-    perp
-```
-
-4. Ask a question
+3. Ask a question
 
 ```shell
 >>> spice chat
@@ -158,7 +135,7 @@ For more detailed local conditions, you can check:
 Time: 18.28s (first token 10.02s). Tokens: 183. Prompt: 160. Completion: 23 (2.78/s).
 ```
 
-5. Check that the LLM did use the internet
+4. Check that the LLM did use the internet
 
 ```shell
 spice trace ai_chat

websearch/spicepod.yaml

@@ -14,13 +14,6 @@ models:
       tools: the_internet
       system_prompt: |
         You have access to the internet. You don't know what day it is today.
-
-  - name: perp
-    from: perplexity:sonar
-    params:
-      perplexity_auth_token: ${ secrets:SPICE_PERPLEXITY_AUTH_TOKEN }
-      system_prompt: |
-        When asked a question with dates, locations or numbers, use an ASCII table when appropriate. Don't overuse it.
 tools:
   - name: the_internet
     from: websearch