chore: update cookbooks (#37)

* fix: update ab-testing cookbook * fix: context relevancy -> context utilization * fix: create a dataset cookbook * fix: evaluate agent runs * fix: distributed tracing * fix: evaluate user satisfaction cookbook * fix: langgraph example cookbook * fix: RAG LlamaIndex cookbook * fix: monitor conversational ai agent * fix: multimodal conversational ai cookbook * fix: add example image * fix: relevancy -> utilization * fix: swap LLMs * fix: literalai version * fix: version literalai * fix: typescript cookbooks versions & co * fix: add experiment comparison
Chainlit · Nov 13, 2024 · d79587a · d79587a
1 parent 42a192f
commit d79587a
Show file tree

Hide file tree

Showing 66 changed files with 9,104 additions and 6,618 deletions.
diff --git a/.gitignore b/.gitignore
@@ -5,5 +5,8 @@
 **/dist
 **/node_modules
 
+# Uvicorn CPython
+**/*.pyc
+
 .env
 .python-version
diff --git a/README.md b/README.md
@@ -14,16 +14,16 @@ For more information, find the full documentation [here](https://docs.getliteral
 
 | Name                                                                                               | Category                           | Description                                                                                                              |
 | -------------------------------------------------------------------------------------------------- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
-| [Context Relevancy with Ragas](/python/context-relevancy-ragas/)                                   | Evaluation                         | Build a RAG application and evaluate this with RAGAS based on context relevancy.                                         |
+| [Context Utilization with Ragas](/python/context-utilization-ragas/)                               | Evaluation                         | Build a RAG application and evaluate it with RAGAS based on context utilization.                                         |
 | [Evaluate User Satisfaction - Customer Support Conversations](/python/evaluate-user-satisfaction/) | Evaluation                         | Retrieve your Customer Support Conversations from Literal AI and evaluate user satisfaction on this conversational data. |
 | [LlamaIndex Integration](/python/llamaindex-integration/)                                          | Observability                      | Build a Q&A application with LLamaIndex and monitor it with Literal AI.                                                  |
 | [Evaluate Agent Runs with Tools](/python/evaluate-agent-runs/)                                     | Observability (Tools) & Evaluation | Build a simple agent which can use two tools. Monitor and evaluate the tool usage.                                       |
 | [A/B Testing Client-Side](/python/ab-testing-client-side/)                                         | Evaluation                         | Build two prompts, randomly assign to new conversations and A/B test on a metric.                                        |
-| [Create a Dataset](/python/create-a-dataset/)                                         | Evaluation                         | Create a Literal AI Dataset from the SDK                                        |
-| [Distributed Tracing](/python/distributed-tracing/)                                         | Observability                         | Trace a distributed (TS and Py) service                                         |
-| [Monitor a Conversational AI agent](/python/monitor-conversational-ai-agent/)                                         | Observability                         | Monitor a Conversational AI agent, built in FastAPI                                         |
-| [Monitor a Multimodal chatbot](/python/multimodal-conversational-ai/)                                         | Observability                         | Monitor a multimodal Conversational AI agent, built with OpenAI                                         |
-| [LangGraph example](/python/langgraph-example/)                                                      | Observability                         |  Example with LangGraph : a graph flow with tool use |
+| [Create a Dataset](/python/create-a-dataset/)                                                      | Evaluation                         | Create a Literal AI Dataset from the SDK                                                                                 |
+| [Distributed Tracing](/python/distributed-tracing/)                                                | Observability                      | Trace a distributed (TS and Py) service                                                                                  |
+| [Monitor a Conversational AI agent](/python/monitor-conversational-ai-agent/)                      | Observability                      | Monitor a Conversational AI agent, built in FastAPI                                                                      |
+| [Monitor a Multimodal chatbot](/python/multimodal-conversational-ai/)                              | Observability                      | Monitor a multimodal Conversational AI agent, built with OpenAI                                                          |
+| [LangGraph example](/python/langgraph-example/)                                                    | Observability                      | Example with LangGraph : a graph flow with tool use                                                                      |
 
 ### TypeScript
 
@@ -35,6 +35,6 @@ For more information, find the full documentation [here](https://docs.getliteral
 | [Chatbot using Next.js, OpenAI and Literal AI](/typescript/nextjs-openai/)                                                | Observablity  | Create a personalized and monitored chatbot with OpenAI, Next.js and Literal AI.                           |
 | [Chatbot using Vercel ai SDK and Literal AI](/typescript/vercel-ai-sdk/)                                                  | Observablity  | Create a personalized and monitored chatbot with Vercel ai SDK and Literal AI.                             |
 | [Simple RAG using LanceDB, OpenAI and Literal AI](/typescript/lancedb-rag)                                                | Observability | Create Simple RAG on Youtube Transcripts stored using LanceDB                                              |
-| [Speech-to-Emoji: Next.js app to summarize audio with OpenAI Whisper, GPT-4o and Literal AI](/typescript/speech-to-emoji) | Observability | Create a simple web app that transcribes and summarizes audio using OpenAI Whisper, GPT-4 and Literal AI.  |
+| [Speech-to-Emoji: Next.js app to summarize audio with OpenAI Whisper, GPT-4o and Literal AI](/typescript/speech-to-emoji) | Observability | Create a simple web app that transcribes and summarizes audio using OpenAI Whisper, GPT-4o and Literal AI. |
 | [Interactive map with a copilot chat bot](/typescript/leaflet-interactive-map/)                                           | Observability | A world map with a chat bot that is context aware and react to the user position on the map                |
 | [LangChain and LangGraph examples](/typescript/langchain-langgraph/)                                                      | Observability | Three examples with LangChain/LangGraph : a basic RAG, a graph flow with tool use, and a multi-agent flow  |
diff --git a/python/ab-testing-client-side/.env.example b/python/ab-testing-client-side/.env.example
@@ -1,3 +1,2 @@
 OPENAI_API_KEY=
 LITERAL_API_KEY=
-LITERAL_API_URL=
diff --git a/python/ab-testing-client-side/README.md b/python/ab-testing-client-side/README.md
@@ -1,15 +1,18 @@
 # Client-side A/B testing two prompts
 
-In this notebook, you will learn how to do a simple A/B test between two different prompts, using Literal AI's Thread observability but running the test client-side.
+In this notebook, you will learn how to do a simple A/B test between two different prompts,
+using Literal AI's Thread observability and running the test client-side.
 
 ## Setup
 
-To install dependencies, run: 
+To install dependencies, run:
+
 ```bash
 pip install -r requirements.txt
-``` 
+```
 
 Create and set your Literal AI and OpenAI API keys in `.env`:
+
 ```bash
 cp .env.example .env
-```
+```
diff --git a/python/ab-testing-client-side/ab-testing-client-side.ipynb b/python/ab-testing-client-side/ab-testing-client-side.ipynb
diff --git a/python/ab-testing-client-side/img/threads.png b/python/ab-testing-client-side/img/threads.png
diff --git a/python/ab-testing-client-side/requirements.txt b/python/ab-testing-client-side/requirements.txt
@@ -1,4 +1,4 @@
 python-dotenv>=1.0.1
-literalai>=0.0.503
+literalai>=0.1.0
 openai
 matplotlib