diff --git a/environment.yml b/environment.yml index 56654d7..7f31d58 100644 --- a/environment.yml +++ b/environment.yml @@ -17,16 +17,13 @@ dependencies: - scikit-learn - chromadb - jupyter-dash - - sentencepiece - pyarrow - pip: - beautifulsoup4 - plotly - - bitsandbytes - transformers - sentence-transformers - - datasets - - accelerate + - datasets==3.6.0 - openai - anthropic - google-generativeai diff --git a/extras/trading/prototype_trader.ipynb b/extras/trading/prototype_trader.ipynb index 30358b9..1143a10 100644 --- a/extras/trading/prototype_trader.ipynb +++ b/extras/trading/prototype_trader.ipynb @@ -346,7 +346,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.11" + "version": "3.11.13" } }, "nbformat": 4, diff --git a/requirements.txt b/requirements.txt index 0f5bd66..1615af4 100644 --- a/requirements.txt +++ b/requirements.txt @@ -14,18 +14,15 @@ tqdm openai gradio langchain -tiktoken +langchain-core +langchain-text-splitters langchain-openai -langchain_experimental -langchain_chroma -langchain[docarray] -datasets -sentencepiece +langchain-chroma +langchain-community +datasets==3.6.0 matplotlib google-generativeai anthropic -scikit-learn -unstructured chromadb plotly jupyter-dash @@ -33,9 +30,6 @@ beautifulsoup4 pydub modal ollama -accelerate -sentencepiece -bitsandbytes psutil setuptools speedtest-cli diff --git a/week2/day1.ipynb b/week2/day1.ipynb index c6d98f4..4939f47 100644 --- a/week2/day1.ipynb +++ b/week2/day1.ipynb @@ -290,12 +290,12 @@ "metadata": {}, "outputs": [], "source": [ - "# If you have access to this, here is the reasoning model o3-mini\n", + "# If you have access to this, here is the reasoning model o4-mini\n", "# This is trained to think through its response before replying\n", "# So it will take longer but the answer should be more reasoned - not that this helps..\n", "\n", "completion = openai.chat.completions.create(\n", - " model='o3-mini',\n", + " model='o4-mini',\n", " messages=prompts\n", ")\n", "print(completion.choices[0].message.content)" @@ -308,12 +308,12 @@ "metadata": {}, "outputs": [], "source": [ - "# Claude 3.7 Sonnet\n", + "# Claude 4.0 Sonnet\n", "# API needs system message provided separately from user prompt\n", "# Also adding max_tokens\n", "\n", "message = claude.messages.create(\n", - " model=\"claude-3-7-sonnet-latest\",\n", + " model=\"claude-sonnet-4-20250514\",\n", " max_tokens=200,\n", " temperature=0.7,\n", " system=system_message,\n", @@ -332,12 +332,12 @@ "metadata": {}, "outputs": [], "source": [ - "# Claude 3.7 Sonnet again\n", + "# Claude 4.0 Sonnet again\n", "# Now let's add in streaming back results\n", "# If the streaming looks strange, then please see the note below this cell!\n", "\n", "result = claude.messages.stream(\n", - " model=\"claude-3-7-sonnet-latest\",\n", + " model=\"claude-sonnet-4-20250514\",\n", " max_tokens=200,\n", " temperature=0.7,\n", " system=system_message,\n", @@ -408,12 +408,28 @@ ")\n", "\n", "response = gemini_via_openai_client.chat.completions.create(\n", - " model=\"gemini-2.5-flash-preview-04-17\",\n", + " model=\"gemini-2.5-flash\",\n", " messages=prompts\n", ")\n", "print(response.choices[0].message.content)" ] }, + { + "cell_type": "markdown", + "id": "492f0ff2-8581-4836-bf00-37fddbe120eb", + "metadata": {}, + "source": [ + "# Sidenote:\n", + "\n", + "This alternative approach of using the client library from OpenAI to connect with other models has become extremely popular in recent months.\n", + "\n", + "So much so, that all the models now support this approach - including Anthropic.\n", + "\n", + "You can read more about this approach, with 4 examples, in the first section of this guide:\n", + "\n", + "https://github.com/ed-donner/agents/blob/main/guides/09_ai_apis_and_ollama.ipynb" + ] + }, { "cell_type": "markdown", "id": "33f70c88-7ca9-470b-ad55-d93a57dcc0ab", @@ -583,7 +599,7 @@ "# Have it stream back results in markdown\n", "\n", "stream = openai.chat.completions.create(\n", - " model='gpt-4o-mini',\n", + " model='gpt-4.1-mini',\n", " messages=prompts,\n", " temperature=0.7,\n", " stream=True\n", @@ -634,11 +650,11 @@ "metadata": {}, "outputs": [], "source": [ - "# Let's make a conversation between GPT-4o-mini and Claude-3-haiku\n", + "# Let's make a conversation between GPT-4.1-mini and Claude-3.5-haiku\n", "# We're using cheap versions of models so the costs will be minimal\n", "\n", - "gpt_model = \"gpt-4o-mini\"\n", - "claude_model = \"claude-3-haiku-20240307\"\n", + "gpt_model = \"gpt-4.1-mini\"\n", + "claude_model = \"claude-3-5-haiku-latest\"\n", "\n", "gpt_system = \"You are a chatbot who is very argumentative; \\\n", "you disagree with anything in the conversation and you challenge everything, in a snarky way.\"\n", @@ -774,6 +790,19 @@ "\n", "Try creating a 3-way, perhaps bringing Gemini into the conversation! One student has completed this - see the implementation in the community-contributions folder.\n", "\n", + "The most reliable way to do this involves thinking a bit differently about your prompts: just 1 system prompt and 1 user prompt each time, and in the user prompt list the full conversation so far.\n", + "\n", + "Something like:\n", + "\n", + "```python\n", + "user_prompt = f\"\"\"\n", + " You are Alex, in conversation with Blake and Charlie.\n", + " The conversation so far is as follows:\n", + " {conversation}\n", + " Now with this, respond with what you would like to say next, as Alex.\n", + " \"\"\"\n", + "```\n", + "\n", "Try doing this yourself before you look at the solutions. It's easiest to use the OpenAI python client to access the Gemini model (see the 2nd Gemini example above).\n", "\n", "## Additional exercise\n", @@ -824,7 +853,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.12" + "version": "3.11.13" } }, "nbformat": 4, diff --git a/week2/day2.ipynb b/week2/day2.ipynb index 801bfe0..00a2840 100644 --- a/week2/day2.ipynb +++ b/week2/day2.ipynb @@ -568,7 +568,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.12" + "version": "3.11.13" } }, "nbformat": 4, diff --git a/week2/day3.ipynb b/week2/day3.ipynb index 2d955f5..9f044b7 100644 --- a/week2/day3.ipynb +++ b/week2/day3.ipynb @@ -301,7 +301,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.11" + "version": "3.11.13" } }, "nbformat": 4, diff --git a/week5/community-contributions/day 4 no_langchain/RAG_chat_no_LangChain.ipynb b/week5/community-contributions/day 4 no_langchain/RAG_chat_no_LangChain.ipynb index 7c2572d..685f7fa 100644 --- a/week5/community-contributions/day 4 no_langchain/RAG_chat_no_LangChain.ipynb +++ b/week5/community-contributions/day 4 no_langchain/RAG_chat_no_LangChain.ipynb @@ -386,7 +386,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.11" + "version": "3.11.13" } }, "nbformat": 4, diff --git a/week5/community-contributions/docuSeekAI/docuSeekAI.ipynb b/week5/community-contributions/docuSeekAI/docuSeekAI.ipynb index fb49ebd..4f16577 100644 --- a/week5/community-contributions/docuSeekAI/docuSeekAI.ipynb +++ b/week5/community-contributions/docuSeekAI/docuSeekAI.ipynb @@ -92,10 +92,24 @@ } ], "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, "language_info": { - "name": "python" + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.11.12" } }, "nbformat": 4, - "nbformat_minor": 2 + "nbformat_minor": 4 } diff --git a/week5/day1.ipynb b/week5/day1.ipynb index 416a1a0..c9d82b0 100644 --- a/week5/day1.ipynb +++ b/week5/day1.ipynb @@ -256,7 +256,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.11" + "version": "3.11.13" } }, "nbformat": 4, diff --git a/week5/day4.5.ipynb b/week5/day4.5.ipynb index 2cad1ed..ea3518c 100644 --- a/week5/day4.5.ipynb +++ b/week5/day4.5.ipynb @@ -27,6 +27,20 @@ "import gradio as gr" ] }, + { + "cell_type": "code", + "execution_count": null, + "id": "94a564ed-5cda-42d9-aada-2a5e85d02d15", + "metadata": {}, + "outputs": [], + "source": [ + "# install faiss-cpu!\n", + "# Mac users - this may fail if you don't have a recent version of MacOS\n", + "# In which case I recommend you skip this lab -- FAISS is not essential! (Or upgrade MacOS if you wish..)\n", + "\n", + "!pip install faiss-cpu" + ] + }, { "cell_type": "code", "execution_count": null, @@ -400,7 +414,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.12" + "version": "3.11.13" } }, "nbformat": 4, diff --git a/week6/day1.ipynb b/week6/day1.ipynb index 3035814..8202845 100644 --- a/week6/day1.ipynb +++ b/week6/day1.ipynb @@ -102,6 +102,18 @@ "%matplotlib inline" ] }, + { + "cell_type": "markdown", + "id": "cd6d801e-d195-45fe-898e-495dbcb19d7d", + "metadata": {}, + "source": [ + "## Load our dataset\n", + "\n", + "In the next cell, we load in the dataset from huggingface.\n", + "\n", + "If this gives you an error like \"trust_remote_code is no longer supported\", then please run this command in a new cell: `!pip install datasets==3.6.0` and then restart the Kernel, and try again." + ] + }, { "cell_type": "code", "execution_count": null, @@ -109,8 +121,6 @@ "metadata": {}, "outputs": [], "source": [ - "# Load in our dataset\n", - "\n", "dataset = load_dataset(\"McAuley-Lab/Amazon-Reviews-2023\", f\"raw_meta_Appliances\", split=\"full\", trust_remote_code=True)" ] }, @@ -429,7 +439,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.12" + "version": "3.11.13" } }, "nbformat": 4, diff --git a/week6/day2.ipynb b/week6/day2.ipynb index 7eb5c8b..d179bff 100644 --- a/week6/day2.ipynb +++ b/week6/day2.ipynb @@ -119,7 +119,7 @@ "source": [ "# Load in the same dataset as last time\n", "\n", - "items = ItemLoader(\"Appliances\").load()" + "items = ItemLoader(\"Home_and_Kitchen\").load()" ] }, { @@ -624,7 +624,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.12" + "version": "3.11.13" } }, "nbformat": 4, diff --git a/week6/day3.ipynb b/week6/day3.ipynb index 9e51979..2170e9d 100644 --- a/week6/day3.ipynb +++ b/week6/day3.ipynb @@ -918,7 +918,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.12" + "version": "3.11.13" } }, "nbformat": 4, diff --git a/week6/day4.ipynb b/week6/day4.ipynb index cb7058f..56885b5 100644 --- a/week6/day4.ipynb +++ b/week6/day4.ipynb @@ -398,7 +398,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.11" + "version": "3.11.13" } }, "nbformat": 4, diff --git a/week6/lite.ipynb b/week6/lite.ipynb index 502d959..1a30deb 100644 --- a/week6/lite.ipynb +++ b/week6/lite.ipynb @@ -427,7 +427,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.12" + "version": "3.11.13" } }, "nbformat": 4, diff --git a/week8/day3.ipynb b/week8/day3.ipynb index 9188717..6f42c0e 100644 --- a/week8/day3.ipynb +++ b/week8/day3.ipynb @@ -227,7 +227,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.11" + "version": "3.11.13" } }, "nbformat": 4, diff --git a/week8/day5.ipynb b/week8/day5.ipynb index 5e11432..d42d181 100644 --- a/week8/day5.ipynb +++ b/week8/day5.ipynb @@ -171,7 +171,7 @@ " If you're not fed up of product prices yet 😂 I've built this out some more!
\n", " If you look in my repo tech2ai, in segment3/lab1 is a neural network implementation of the pricer in pure PyTorch. It does pretty well..
\n", " And if you look in my repo Agentic in the workshop folder is the same Agent project taken further. There's a new version of the PlanningAgent called AutonomousPlanningAgent that uses multiple Tools, and a MessagingAgent that uses claude-3.7 to write texts. The AutonomousPlanningAgent uses the fantastic OpenAI Agents SDK and the mighty MCP protocol from Anthropic.
\n", - " If you're intrigued by Agents and MCP, and would like to learn more, then I also have a companion course called the Complete Agentic AI Engineering Course that might interest you (if you haven't had enough of me by now!!)\n", + " If you're intrigued by Agents and MCP, and would like to learn more, then I also have a companion course called the Complete Agentic AI Engineering Course that might interest you (if you haven't had enough of me by now!!), and also another course for leaders and founders looking to build a valuable business with LLMs.\n", " \n", " \n", " \n", @@ -223,7 +223,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.12" + "version": "3.11.13" } }, "nbformat": 4,