Tools: TxtAI got skills

Install dependencies ## Define a skill.md file ## Query for TxtAI questions ## Wrapping up This example will demonstrate how to use txtai agents with skill.md files. We'll setup a skill.md file with details on how to use TxtAI and run a series of agent requests. Install txtai and all dependencies. Next, we'll create our skill.md file. This file has examples on how to build embeddings databases, how to use re-ranker pipelines, RAG pipelines and more. The upside of a skill.md file vs an agents.md file is that it can be dynamically added to the agent context. The description helps the agent decide if the skill is necessary given the request. Think of it like a dynamic knowledge base that's easy to modify. Now, let's try this out and see if the LLM is smart enough to use the defined skill vs. going out on the web. Let's setup the scaffolding code to create and run an agent. We'll use a Qwen3 4B non-thinking LLM as the agent's model. We'll add the websearch and webview tools to the agent along with the skill.md file previously created. Additionally, we'll add a sliding window of the last 2 responses as "agent memory". This will help create a rolling dialogue. First, we'll ask how to build a TxtAI embeddings database. To create a txtai embeddings program that indexes data, use the following Python code: This program initializes an embeddings database using the sentence-transformers/nli-mpnet-base-v2 model and indexes a list of text data. The indexed data can later be searched or used in other applications like retrieval, RAG, or translation. The Agent pulled the correct section from the skill.md file. Now, let's look for an example on how to use a re-ranker pipeline. Great! This also works. But remember we have access to an LLM here. It doesn't have to blindly just pull the text. Let's ask it to modify the last example. Notice it just edited the code with a different reranker model and even added a comment to note this change. We can also clear the rolling dialogue and start fresh. This example shows how to add a skill.md file to txtai agents. Go give it a try! Templates let you quickly answer FAQs or store snippets for re-use. Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink. Hide child comments as well For further actions, you may consider blocking this person and/or reporting abuse CODE_BLOCK: %%capture !pip install txtai[agent] Enter fullscreen mode Exit fullscreen mode CODE_BLOCK: %%capture !pip install txtai[agent] CODE_BLOCK: %%capture !pip install txtai[agent] COMMAND_BLOCK: --- name: txtai description: "Examples on how to build txtai embeddings databases, txtai RAG pipelines, txtai reranker pipelines and txtai translation pipelines" --- # Build an embeddings database from txtai import Embeddings # Create embeddings model, backed by sentence-transformers & transformers embeddings = Embeddings(path="sentence-transformers/nli-mpnet-base-v2") data = [ "US tops 5 million confirmed virus cases", "Canada's last fully intact ice shelf has suddenly collapsed, " + "forming a Manhattan-sized iceberg", "Beijing mobilises invasion craft along coast as Taiwan tensions escalate", "The National Park Service warns against sacrificing slower friends " + "in a bear attack", "Maine man wins $1M from $25 lottery ticket", "Make huge profits without work, earn up to $100,000 a day" ] # Index the list of text embeddings.index(data) # Search an embeddings database embeddings.search("Search query") # Build a RAG pipeline from txtai import Embeddings, RAG # Input data data = [ "US tops 5 million confirmed virus cases", "Canada's last fully intact ice shelf has suddenly collapsed, " + "forming a Manhattan-sized iceberg", "Beijing mobilises invasion craft along coast as Taiwan tensions escalate", "The National Park Service warns against sacrificing slower friends " + "in a bear attack", "Maine man wins $1M from $25 lottery ticket", "Make huge profits without work, earn up to $100,000 a day" ] # Build embeddings index embeddings = Embeddings(content=True) embeddings.index(data) # Create the RAG pipeline rag = RAG(embeddings, "Qwen/Qwen3-0.6B", template=""" Answer the following question using the provided context. Question: {question} Context: {context} """) # Run RAG pipeline rag("What was won?") # Translate text from English into French from txtai.pipeline import Translation # Create and run pipeline translate = Translation() translate("This is a test translation", "fr") # Re-ranker pipeline from txtai import Embeddings from txtai.pipeline import Reranker, Similarity # Embeddings instance embeddings = Embeddings() embeddings.load(provider="huggingface-hub", container="neuml/txtai-wikipedia") # Similarity instance similarity = Similarity(path="colbert-ir/colbertv2.0", lateencode=True) # Reranking pipeline reranker = Reranker(embeddings, similarity) reranker("Tell me about AI") Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: --- name: txtai description: "Examples on how to build txtai embeddings databases, txtai RAG pipelines, txtai reranker pipelines and txtai translation pipelines" --- # Build an embeddings database from txtai import Embeddings # Create embeddings model, backed by sentence-transformers & transformers embeddings = Embeddings(path="sentence-transformers/nli-mpnet-base-v2") data = [ "US tops 5 million confirmed virus cases", "Canada's last fully intact ice shelf has suddenly collapsed, " + "forming a Manhattan-sized iceberg", "Beijing mobilises invasion craft along coast as Taiwan tensions escalate", "The National Park Service warns against sacrificing slower friends " + "in a bear attack", "Maine man wins $1M from $25 lottery ticket", "Make huge profits without work, earn up to $100,000 a day" ] # Index the list of text embeddings.index(data) # Search an embeddings database embeddings.search("Search query") # Build a RAG pipeline from txtai import Embeddings, RAG # Input data data = [ "US tops 5 million confirmed virus cases", "Canada's last fully intact ice shelf has suddenly collapsed, " + "forming a Manhattan-sized iceberg", "Beijing mobilises invasion craft along coast as Taiwan tensions escalate", "The National Park Service warns against sacrificing slower friends " + "in a bear attack", "Maine man wins $1M from $25 lottery ticket", "Make huge profits without work, earn up to $100,000 a day" ] # Build embeddings index embeddings = Embeddings(content=True) embeddings.index(data) # Create the RAG pipeline rag = RAG(embeddings, "Qwen/Qwen3-0.6B", template=""" Answer the following question using the provided context. Question: {question} Context: {context} """) # Run RAG pipeline rag("What was won?") # Translate text from English into French from txtai.pipeline import Translation # Create and run pipeline translate = Translation() translate("This is a test translation", "fr") # Re-ranker pipeline from txtai import Embeddings from txtai.pipeline import Reranker, Similarity # Embeddings instance embeddings = Embeddings() embeddings.load(provider="huggingface-hub", container="neuml/txtai-wikipedia") # Similarity instance similarity = Similarity(path="colbert-ir/colbertv2.0", lateencode=True) # Reranking pipeline reranker = Reranker(embeddings, similarity) reranker("Tell me about AI") COMMAND_BLOCK: --- name: txtai description: "Examples on how to build txtai embeddings databases, txtai RAG pipelines, txtai reranker pipelines and txtai translation pipelines" --- # Build an embeddings database from txtai import Embeddings # Create embeddings model, backed by sentence-transformers & transformers embeddings = Embeddings(path="sentence-transformers/nli-mpnet-base-v2") data = [ "US tops 5 million confirmed virus cases", "Canada's last fully intact ice shelf has suddenly collapsed, " + "forming a Manhattan-sized iceberg", "Beijing mobilises invasion craft along coast as Taiwan tensions escalate", "The National Park Service warns against sacrificing slower friends " + "in a bear attack", "Maine man wins $1M from $25 lottery ticket", "Make huge profits without work, earn up to $100,000 a day" ] # Index the list of text embeddings.index(data) # Search an embeddings database embeddings.search("Search query") # Build a RAG pipeline from txtai import Embeddings, RAG # Input data data = [ "US tops 5 million confirmed virus cases", "Canada's last fully intact ice shelf has suddenly collapsed, " + "forming a Manhattan-sized iceberg", "Beijing mobilises invasion craft along coast as Taiwan tensions escalate", "The National Park Service warns against sacrificing slower friends " + "in a bear attack", "Maine man wins $1M from $25 lottery ticket", "Make huge profits without work, earn up to $100,000 a day" ] # Build embeddings index embeddings = Embeddings(content=True) embeddings.index(data) # Create the RAG pipeline rag = RAG(embeddings, "Qwen/Qwen3-0.6B", template=""" Answer the following question using the provided context. Question: {question} Context: {context} """) # Run RAG pipeline rag("What was won?") # Translate text from English into French from txtai.pipeline import Translation # Create and run pipeline translate = Translation() translate("This is a test translation", "fr") # Re-ranker pipeline from txtai import Embeddings from txtai.pipeline import Reranker, Similarity # Embeddings instance embeddings = Embeddings() embeddings.load(provider="huggingface-hub", container="neuml/txtai-wikipedia") # Similarity instance similarity = Similarity(path="colbert-ir/colbertv2.0", lateencode=True) # Reranking pipeline reranker = Reranker(embeddings, similarity) reranker("Tell me about AI") CODE_BLOCK: from txtai import Agent from IPython.display import display, Markdown def run(query, reset=False): answer = agent(query, maxlength=50000, reset=reset) display(Markdown(answer)) agent = Agent( model="Qwen/Qwen3-4B-Instruct-2507", tools=["websearch", "webview", "skill.md"], memory=2, verbosity_level=0 ) Enter fullscreen mode Exit fullscreen mode CODE_BLOCK: from txtai import Agent from IPython.display import display, Markdown def run(query, reset=False): answer = agent(query, maxlength=50000, reset=reset) display(Markdown(answer)) agent = Agent( model="Qwen/Qwen3-4B-Instruct-2507", tools=["websearch", "webview", "skill.md"], memory=2, verbosity_level=0 ) CODE_BLOCK: from txtai import Agent from IPython.display import display, Markdown def run(query, reset=False): answer = agent(query, maxlength=50000, reset=reset) display(Markdown(answer)) agent = Agent( model="Qwen/Qwen3-4B-Instruct-2507", tools=["websearch", "webview", "skill.md"], memory=2, verbosity_level=0 ) CODE_BLOCK: run("Write a txtai embeddings program that indexes data") Enter fullscreen mode Exit fullscreen mode CODE_BLOCK: run("Write a txtai embeddings program that indexes data") CODE_BLOCK: run("Write a txtai embeddings program that indexes data") COMMAND_BLOCK: from txtai import Embeddings # Create embeddings model using sentence-transformers embeddings = Embeddings(path="sentence-transformers/nli-mpnet-base-v2") # Sample data to index data = [ "US tops 5 million confirmed virus cases", "Canada's last fully intact ice shelf has suddenly collapsed, " + "forming a Manhattan-sized iceberg", "Beijing mobilises invasion craft along coast as Taiwan tensions escalate", "The National Park Service warns against sacrificing slower friends " + "in a bear attack", "Maine man wins $1M from $25 lottery ticket", "Make huge profits without work, earn up to $100,000 a day" ] # Index the data embeddings.index(data) Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: from txtai import Embeddings # Create embeddings model using sentence-transformers embeddings = Embeddings(path="sentence-transformers/nli-mpnet-base-v2") # Sample data to index data = [ "US tops 5 million confirmed virus cases", "Canada's last fully intact ice shelf has suddenly collapsed, " + "forming a Manhattan-sized iceberg", "Beijing mobilises invasion craft along coast as Taiwan tensions escalate", "The National Park Service warns against sacrificing slower friends " + "in a bear attack", "Maine man wins $1M from $25 lottery ticket", "Make huge profits without work, earn up to $100,000 a day" ] # Index the data embeddings.index(data) COMMAND_BLOCK: from txtai import Embeddings # Create embeddings model using sentence-transformers embeddings = Embeddings(path="sentence-transformers/nli-mpnet-base-v2") # Sample data to index data = [ "US tops 5 million confirmed virus cases", "Canada's last fully intact ice shelf has suddenly collapsed, " + "forming a Manhattan-sized iceberg", "Beijing mobilises invasion craft along coast as Taiwan tensions escalate", "The National Park Service warns against sacrificing slower friends " + "in a bear attack", "Maine man wins $1M from $25 lottery ticket", "Make huge profits without work, earn up to $100,000 a day" ] # Index the data embeddings.index(data) CODE_BLOCK: run("Write a txtai re-ranker pipeline") Enter fullscreen mode Exit fullscreen mode CODE_BLOCK: run("Write a txtai re-ranker pipeline") CODE_BLOCK: run("Write a txtai re-ranker pipeline") COMMAND_BLOCK: from txtai import Embeddings from txtai.pipeline import Reranker, Similarity # Embeddings instance embeddings = Embeddings() embeddings.load(provider="huggingface-hub", container="neuml/txtai-wikipedia") # Similarity instance similarity = Similarity(path="colbert-ir/colbertv2.0", lateencode=True) # Reranking pipeline reranker = Reranker(embeddings, similarity) reranker("Tell me about AI") Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: from txtai import Embeddings from txtai.pipeline import Reranker, Similarity # Embeddings instance embeddings = Embeddings() embeddings.load(provider="huggingface-hub", container="neuml/txtai-wikipedia") # Similarity instance similarity = Similarity(path="colbert-ir/colbertv2.0", lateencode=True) # Reranking pipeline reranker = Reranker(embeddings, similarity) reranker("Tell me about AI") COMMAND_BLOCK: from txtai import Embeddings from txtai.pipeline import Reranker, Similarity # Embeddings instance embeddings = Embeddings() embeddings.load(provider="huggingface-hub", container="neuml/txtai-wikipedia") # Similarity instance similarity = Similarity(path="colbert-ir/colbertv2.0", lateencode=True) # Reranking pipeline reranker = Reranker(embeddings, similarity) reranker("Tell me about AI") CODE_BLOCK: run("Update the similarity path to use another reranker model. Disable lateencode.") Enter fullscreen mode Exit fullscreen mode CODE_BLOCK: run("Update the similarity path to use another reranker model. Disable lateencode.") CODE_BLOCK: run("Update the similarity path to use another reranker model. Disable lateencode.") COMMAND_BLOCK: from txtai import Embeddings from txtai.pipeline import Reranker, Similarity # Embeddings instance embeddings = Embeddings() embeddings.load(provider="huggingface-hub", container="neuml/txtai-wikipedia") # Similarity instance with a different reranker model and lateencode disabled similarity = Similarity(path="BAAI/bge-reranker-base", lateencode=False) # Reranking pipeline reranker = Reranker(embeddings, similarity) reranker("Tell me about AI") Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: from txtai import Embeddings from txtai.pipeline import Reranker, Similarity # Embeddings instance embeddings = Embeddings() embeddings.load(provider="huggingface-hub", container="neuml/txtai-wikipedia") # Similarity instance with a different reranker model and lateencode disabled similarity = Similarity(path="BAAI/bge-reranker-base", lateencode=False) # Reranking pipeline reranker = Reranker(embeddings, similarity) reranker("Tell me about AI") COMMAND_BLOCK: from txtai import Embeddings from txtai.pipeline import Reranker, Similarity # Embeddings instance embeddings = Embeddings() embeddings.load(provider="huggingface-hub", container="neuml/txtai-wikipedia") # Similarity instance with a different reranker model and lateencode disabled similarity = Similarity(path="BAAI/bge-reranker-base", lateencode=False) # Reranking pipeline reranker = Reranker(embeddings, similarity) reranker("Tell me about AI") CODE_BLOCK: run("Write a txtai program that translate text from English to Spanish", reset=True) Enter fullscreen mode Exit fullscreen mode CODE_BLOCK: run("Write a txtai program that translate text from English to Spanish", reset=True) CODE_BLOCK: run("Write a txtai program that translate text from English to Spanish", reset=True) COMMAND_BLOCK: from txtai.pipeline import Translation # Create and run pipeline for English to Spanish translation translate = Translation() translated_text = translate("This is a test translation", "es") print(translated_text) Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: from txtai.pipeline import Translation # Create and run pipeline for English to Spanish translation translate = Translation() translated_text = translate("This is a test translation", "es") print(translated_text) COMMAND_BLOCK: from txtai.pipeline import Translation # Create and run pipeline for English to Spanish translation translate = Translation() translated_text = translate("This is a test translation", "es") print(translated_text)