Merge branch 'main' into multimodal-agent

deepset-ai · Nov 11, 2024 · eb08814 · eb08814
2 parents c70fc85 + d7b5d6c
commit eb08814
Show file tree

Hide file tree

Showing 6 changed files with 449 additions and 4 deletions.
diff --git a/index.toml b/index.toml
@@ -278,4 +278,10 @@ discuss = "https://github.com/deepset-ai/haystack-experimental/discussions/74"
 title = "Multimodal Agent with fastRAG and Haystack"
 notebook = "multimodal_agent_with_fastrag_haystack.ipynb"
 new = true
-topics = ["Multimodal", "Agents"]
+topics = ["Multimodal", "Agents"]
+
+[[cookbook]]
+title = "Web-Enhanced Self-Reflecting Agent"
+notebook = "web_enhanced_self_reflecting_agent.ipynb"
+topics = ["Agents"]
+
diff --git a/notebooks/extracting_metadata_filters_from_a_user_query.ipynb b/notebooks/extracting_metadata_filters_from_a_user_query.ipynb
@@ -10,7 +10,15 @@
         "\n",
         "*Notebook by [David Batista](https://www.linkedin.com/in/dsbatista)*\n",
         "\n",
-        "> 📚 This cookbook has an accompanying article with a complete walkthrough [\"Advanced Retrieval: Extract Metadata from Queries to Improve Retrieval\"](https://haystack.deepset.ai/blog/extracting-metadata-filter)\n",
+        "> This is part one of the **Advanced Use Cases** series:\n",
+        ">\n",
+        "> 1️⃣ **Extract Metadata from Queries to Improve Retrieval & the [full article](/blog/extracting-metadata-filter)**\n",
+        ">\n",
+        "> 2️⃣ Query Expansion [cookbook](/cookbook/query-expansion) & [full article](/blog/query-expansion)\n",
+        ">\n",
+        "> 3️⃣ Query Decomposition [cookbook](/cookbook/query_decomposition) & the [full article](/blog/query-decomposition)\n",
+        ">\n",
+        "> 4️⃣ [Automated Metadata Enrichment](/cookbook/metadata_enrichment)\n",
         "\n",
         "In this notebook, we'll discuss how to implement a custom component, `QueryMetadataExtractor`, that extracts entities from the query and formulates the corresponding metadata filter.\n",
         "\n",

diff --git a/notebooks/metadata_enrichment.ipynb b/notebooks/metadata_enrichment.ipynb
@@ -10,13 +10,27 @@
         "\n",
         "by Tuana Celik ([LI](https://www.linkedin.com/in/tuanacelik/), [Twitter](https://x.com/tuanacelik))\n",
         "\n",
+        "> This is part one of the **Advanced Use Cases** series:\n",
+        ">\n",
+        "> 1️⃣ Extract Metadata from Queries to Improve Retrieval [cookbook](/cookbook/extracting_metadata_filters_from_a_user_query) & [full article](/blog/extracting-metadata-filter)\n",
+        ">\n",
+        "> 2️⃣ Query Expansion [cookbook](/cookbook/query-expansion) & [full article](/blog/query-expansion)\n",
+        ">\n",
+        "> 3️⃣ Query Decomposition [cookbook](/cookbook/query_decomposition) & the [full article](/blog/query-decomposition)\n",
+        ">\n",
+        "> 4️⃣ **Automated Metadata Enrichment**\n",
+        "\n",
         "In this example, you'll see how you can make use of structured outputs which is an option for some LLMs, and a custom Haystack component, to automate the enrichment of metadata from documents.\n",
         "\n",
         "You will see how you can define your own metadata fields as a Pydantic Model, as well as the data types each field should have. Finally, you will get a custom `MetadataEnricher` to extract the required fields and add them to the document meta information.\n",
         "\n",
         "In this example, we will be enriching metadata with information relating the funding announements.\n",
         "\n",
-        "Once we populate the metadata of a document with our own fields, we are able to use Metadata Filtering during the retrieval step of RAG pipelines. We can even combine this with [Metadata Extraction from Queries to Improve Retrieval](https://haystack.deepset.ai/blog/extracting-metadata-filter) to be very precise about what documents we are providing as context to an LLM."
+        "Once we populate the metadata of a document with our own fields, we are able to use Metadata Filtering during the retrieval step of RAG pipelines. We can even combine this with [Metadata Extraction from Queries to Improve Retrieval](https://haystack.deepset.ai/blog/extracting-metadata-filter) to be very precise about what documents we are providing as context to an LLM.\n",
+        "\n",
+        "## 📺 Code Along\n",
+        "\n",
+        "<iframe width=\"560\" height=\"315\" src=\"https://www.youtube.com/embed/vk0U1V-cBK0?si=-MHeM23RRfdlAlgm\" title=\"YouTube video player\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen></iframe>"
       ]
     },
     {

diff --git a/notebooks/query-expansion.ipynb b/notebooks/query-expansion.ipynb
@@ -9,6 +9,16 @@
         "# Advanced RAG: Query Expansion\n",
         "_by Tuana Celik ([LI](https://www.linkedin.com/in/tuanacelik/),  [Twitter/X](https://x.com/tuanacelik))_\n",
         "\n",
+        "> This is part one of the **Advanced Use Cases** series:\n",
+        ">\n",
+        "> 1️⃣ Extract Metadata from Queries to Improve Retrieval [cookbook](/cookbook/extracting_metadata_filters_from_a_user_query) & [full article](/blog/extracting-metadata-filter)\n",
+        ">\n",
+        "> 2️⃣ **Query Expansion & the [full article](/blog/query-expansion)**\n",
+        ">\n",
+        "> 3️⃣ Query Decomposition [cookbook](/cookbook/query_decomposition) & [full article](/blog/query-decomposition)\n",
+        ">\n",
+        "> 4️⃣ [Automated Metadata Enrichment](/cookbook/metadata_enrichment)\n",
+        "\n",
         "In this cookbook, you'll learn how to implement query expansion for RAG. Query expansion consists of asking an LLM to produce a number of similar queries to a user query. We are then able to use each of these queries in the retrieval process, increasing the number and relevance of retrieved documents.\n",
         "\n",
         "📚 [Read the full article](https://haystack.deepset.ai/blog/query-expansion)"
@@ -649,7 +659,8 @@
       "provenance": []
     },
     "kernelspec": {
-      "display_name": "Python 3",
+      "display_name": "deeplearning",
+      "language": "python",
       "name": "python3"
     },
     "language_info": {

diff --git a/notebooks/query_decomposition.ipynb b/notebooks/query_decomposition.ipynb
@@ -10,6 +10,16 @@
         "\n",
         "by Tuana Celik ([LI](https://www.linkedin.com/in/tuanacelik/), [Twitter](https://x.com/tuanacelik))\n",
         "\n",
+        "> This is part one of the **Advanced Use Cases** series:\n",
+        ">\n",
+        "> 1️⃣ Extract Metadata from Queries to Improve Retrieval [cookbook](/cookbook/extracting_metadata_filters_from_a_user_query) & [full article](/blog/extracting-metadata-filter)\n",
+        ">\n",
+        "> 2️⃣ Query Expansion [cookbook](/cookbook/query-expansion) & [full article](/blog/query-expansion)\n",
+        ">\n",
+        "> 3️⃣ **Query Decomposition & the [full article](/blog/query-decomposition)**\n",
+        ">\n",
+        "> 4️⃣ [Automated Metadata Enrichment](/cookbook/metadata_enrichment)\n",
+        "\n",
         "Query decomposition is a technique we can use to decompose complex queries into simpler steps, answering each sub-question, and getting an LLM to reason about the final answer based on the answers to the sub-questions.\n",
         "\n",
         "In this recipe, we're using the structured output functionality (currently in beta) by OpenAI to construct `Questions` which lists the sub-questions based on the original question, as well as keeping track of the intermediate answers to each question.\n",

diff --git a/notebooks/web_enhanced_self_reflecting_agent.ipynb b/notebooks/web_enhanced_self_reflecting_agent.ipynb