Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

CorrectiveRAG Notebook Error fixes #16422

Merged
merged 2 commits into from
Oct 8, 2024
+15 −13
Merged

CorrectiveRAG Notebook Error fixes #16422

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1ed48e9
`ctx.get("relevancy_pipeline").run(...` and `ctx.get("tavily_tool").s…
tevfikcagridural Oct 8, 2024
9754a5e
linting
logan-markewich Oct 8, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 5 additions & 3 deletions docs/docs/examples/workflow/corrective_rag_pack.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -265,7 +265,7 @@
"\n",
" index = await ctx.get(\"index\", default=None)\n",
" tavily_tool = await ctx.get(\"tavily_tool\", default=None)\n",
" if not (index or tavily_tool)\n",
" if not (index or tavily_tool):\n",
" raise ValueError(\n",
" \"Index and tavily tool must be constructed. Run with 'documents' and 'tavily_ai_apikey' params first.\"\n",
" )\n",
Expand All @@ -288,7 +288,8 @@
"\n",
" relevancy_results = []\n",
" for node in retrieved_nodes:\n",
" relevancy = await ctx.get(\"relevancy_pipeline\").run(\n",
" relevancy_pipeline = await ctx.get(\"relevancy_pipeline\")\n",
" relevancy = relevancy_pipeline.run(\n",
" context_str=node.text, query_str=query_str\n",
" )\n",
" relevancy_results.append(relevancy.message.content.lower().strip())\n",
Expand Down Expand Up @@ -327,7 +328,8 @@
" qp = await ctx.get(\"transform_query_pipeline\")\n",
" transformed_query_str = (qp.run(query_str=query_str).message.content)\n",
" # Conduct a search with the transformed query string and collect the results.\n",
" search_results = await ctx.get(\"tavily_tool\").search(\n",
" tavily_tool = await ctx.get(\"tavily_tool\")\n",
" search_results = tavily_tool.search(\n",
" transformed_query_str, max_results=5\n",
" )\n",
" search_text = \"\\n\".join([result.text for result in search_results])\n",
Expand Down
Loading