Page MenuHomePhorge
Files F85649016

No OneTemporary
Actions

Size
11 KB
Referenced Files
None
Subscribers
None

View Options

diff --git a/lib/pleroma/search/meilisearch.ex b/lib/pleroma/search/meilisearch.ex
index 9bba5b30f..fb8fdea1b 100644
--- a/lib/pleroma/search/meilisearch.ex
+++ b/lib/pleroma/search/meilisearch.ex
@@ -1,198 +1,194 @@
defmodule Pleroma.Search.Meilisearch do
require Logger
require Pleroma.Constants
alias Pleroma.Activity
alias Pleroma.Config.Getting, as: Config
+ alias Pleroma.Object
import Pleroma.Search.DatabaseSearch
import Ecto.Query
@behaviour Pleroma.Search.SearchBackend
@impl true
def create_index, do: :ok
@impl true
def drop_index, do: :ok
defp meili_headers do
private_key = Config.get([Pleroma.Search.Meilisearch, :private_key])
[{"Content-Type", "application/json"}] ++
if is_nil(private_key), do: [], else: [{"Authorization", "Bearer #{private_key}"}]
end
def meili_get(path) do
endpoint = Config.get([Pleroma.Search.Meilisearch, :url])
result =
Pleroma.HTTP.get(
Path.join(endpoint, path),
meili_headers()
)
with {:ok, res} <- result do
{:ok, Jason.decode!(res.body)}
end
end
def meili_post(path, params) do
endpoint = Config.get([Pleroma.Search.Meilisearch, :url])
result =
Pleroma.HTTP.post(
Path.join(endpoint, path),
Jason.encode!(params),
meili_headers()
)
with {:ok, res} <- result do
{:ok, Jason.decode!(res.body)}
end
end
def meili_put(path, params) do
endpoint = Config.get([Pleroma.Search.Meilisearch, :url])
result =
Pleroma.HTTP.request(
:put,
Path.join(endpoint, path),
Jason.encode!(params),
meili_headers(),
[]
)
with {:ok, res} <- result do
{:ok, Jason.decode!(res.body)}
end
end
def meili_delete(path) do
endpoint = Config.get([Pleroma.Search.Meilisearch, :url])
with {:ok, _} <-
Pleroma.HTTP.request(
:delete,
Path.join(endpoint, path),
"",
meili_headers(),
[]
) do
:ok
else
_ -> {:error, "Could not remove from index"}
end
end
@impl true
def search(user, query, options \\ []) do
limit = Enum.min([Keyword.get(options, :limit), 40])
offset = Keyword.get(options, :offset, 0)
author = Keyword.get(options, :author)
res =
meili_post(
"/indexes/objects/search",
%{q: query, offset: offset, limit: limit}
)
with {:ok, result} <- res do
hits = result["hits"] |> Enum.map(& &1["ap"])
try do
hits
|> Activity.create_by_object_ap_id()
|> Activity.with_preloaded_object()
|> Activity.restrict_deactivated_users()
|> maybe_restrict_local(user)
|> maybe_restrict_author(author)
|> maybe_restrict_blocked(user)
|> maybe_fetch(user, query)
|> order_by([object: obj], desc: obj.data["published"])
|> Pleroma.Repo.all()
rescue
_ -> maybe_fetch([], user, query)
end
end
end
def object_to_search_data(object) do
# Only index public or unlisted Notes
if not is_nil(object) and object.data["type"] == "Note" and
not is_nil(object.data["content"]) and
(Pleroma.Constants.as_public() in object.data["to"] or
Pleroma.Constants.as_public() in object.data["cc"]) and
object.data["content"] not in ["", "."] do
data = object.data
content_str =
case data["content"] do
[nil | rest] -> to_string(rest)
str -> str
end
content =
with {:ok, scrubbed} <-
FastSanitize.Sanitizer.scrub(content_str, Pleroma.HTML.Scrubber.SearchIndexing),
trimmed <- String.trim(scrubbed) do
trimmed
end
# Make sure we have a non-empty string
if content != "" do
{:ok, published, _} = DateTime.from_iso8601(data["published"])
%{
id: object.id,
content: content,
ap: data["id"],
published: published |> DateTime.to_unix()
}
end
end
end
@impl true
- def add_to_index(activity) do
- maybe_search_data = object_to_search_data(activity.object)
-
- if activity.data["type"] == "Create" and maybe_search_data do
- result =
- meili_put(
- "/indexes/objects/documents",
- [maybe_search_data]
- )
-
- with {:ok, %{"status" => "enqueued"}} <- result do
- # Added successfully
- :ok
- else
- _ ->
- # There was an error, report it
- Logger.error("Failed to add activity #{activity.id} to index: #{inspect(result)}")
- {:error, result}
- end
- else
- # The post isn't something we can search, that's ok
+ def add_to_index(%Activity{object: %Object{} = object} = activity) do
+ search_data = object_to_search_data(object)
+
+ result =
+ meili_put(
+ "/indexes/objects/documents",
+ [search_data]
+ )
+
+ with {:ok, %{"status" => "enqueued"}} <- result do
+ # Added successfully
:ok
+ else
+ _ ->
+ # There was an error, report it
+ Logger.error("Failed to add activity #{activity.id} to index: #{inspect(result)}")
+ {:error, result}
end
end
@impl true
def remove_from_index(object) do
meili_delete("/indexes/objects/documents/#{object.id}")
end
@impl true
def healthcheck_endpoints do
endpoint =
Config.get([Pleroma.Search.Meilisearch, :url])
|> URI.parse()
|> Map.put(:path, "/health")
|> URI.to_string()
[endpoint]
end
end
diff --git a/lib/pleroma/search/qdrant_search.ex b/lib/pleroma/search/qdrant_search.ex
index b659bb682..f00475799 100644
--- a/lib/pleroma/search/qdrant_search.ex
+++ b/lib/pleroma/search/qdrant_search.ex
@@ -1,182 +1,178 @@
defmodule Pleroma.Search.QdrantSearch do
@behaviour Pleroma.Search.SearchBackend
import Ecto.Query
alias Pleroma.Activity
alias Pleroma.Config.Getting, as: Config
+ alias Pleroma.Object
alias __MODULE__.OpenAIClient
alias __MODULE__.QdrantClient
import Pleroma.Search.Meilisearch, only: [object_to_search_data: 1]
import Pleroma.Search.DatabaseSearch, only: [maybe_fetch: 3]
@impl true
def create_index do
payload = Config.get([Pleroma.Search.QdrantSearch, :qdrant_index_configuration])
with {:ok, %{status: 200}} <- QdrantClient.put("/collections/posts", payload) do
:ok
else
e -> {:error, e}
end
end
@impl true
def drop_index do
with {:ok, %{status: 200}} <- QdrantClient.delete("/collections/posts") do
:ok
else
e -> {:error, e}
end
end
def get_embedding(text) do
with {:ok, %{body: %{"data" => [%{"embedding" => embedding}]}}} <-
OpenAIClient.post("/v1/embeddings", %{
input: text,
model: Config.get([Pleroma.Search.QdrantSearch, :openai_model])
}) do
{:ok, embedding}
else
_ ->
{:error, "Failed to get embedding"}
end
end
defp actor_from_activity(%{data: %{"actor" => actor}}) do
actor
end
defp actor_from_activity(_), do: nil
defp build_index_payload(activity, embedding) do
actor = actor_from_activity(activity)
published_at = activity.data["published"]
%{
points: [
%{
id: activity.id |> FlakeId.from_string() |> Ecto.UUID.cast!(),
vector: embedding,
payload: %{actor: actor, published_at: published_at}
}
]
}
end
defp build_search_payload(embedding, options) do
base = %{
vector: embedding,
limit: options[:limit] || 20,
offset: options[:offset] || 0
}
if author = options[:author] do
Map.put(base, :filter, %{
must: [%{key: "actor", match: %{value: author.ap_id}}]
})
else
base
end
end
@impl true
- def add_to_index(activity) do
- # This will only index public or unlisted notes
- maybe_search_data = object_to_search_data(activity.object)
-
- if activity.data["type"] == "Create" and maybe_search_data do
- with {:ok, embedding} <- get_embedding(maybe_search_data.content),
- {:ok, %{status: 200}} <-
- QdrantClient.put(
- "/collections/posts/points",
- build_index_payload(activity, embedding)
- ) do
- :ok
- else
- e -> {:error, e}
- end
- else
+ def add_to_index(%Activity{object: %Object{} = object} = activity) do
+ search_data = object_to_search_data(object)
+
+ with {:ok, embedding} <- get_embedding(search_data.content),
+ {:ok, %{status: 200}} <-
+ QdrantClient.put(
+ "/collections/posts/points",
+ build_index_payload(activity, embedding)
+ ) do
:ok
+ else
+ e -> {:error, e}
end
end
@impl true
def remove_from_index(object) do
activity = Activity.get_by_object_ap_id_with_object(object.data["id"])
id = activity.id |> FlakeId.from_string() |> Ecto.UUID.cast!()
with {:ok, %{status: 200}} <-
QdrantClient.post("/collections/posts/points/delete", %{"points" => [id]}) do
:ok
else
e -> {:error, e}
end
end
@impl true
def search(user, original_query, options) do
query = "Represent this sentence for searching relevant passages: #{original_query}"
with {:ok, embedding} <- get_embedding(query),
{:ok, %{body: %{"result" => result}}} <-
QdrantClient.post(
"/collections/posts/points/search",
build_search_payload(embedding, options)
) do
ids =
Enum.map(result, fn %{"id" => id} ->
Ecto.UUID.dump!(id)
end)
from(a in Activity, where: a.id in ^ids)
|> Activity.with_preloaded_object()
|> Activity.restrict_deactivated_users()
|> Ecto.Query.order_by([a], fragment("array_position(?, ?)", ^ids, a.id))
|> Pleroma.Repo.all()
|> maybe_fetch(user, original_query)
else
_ ->
[]
end
end
@impl true
def healthcheck_endpoints do
qdrant_health =
Config.get([Pleroma.Search.QdrantSearch, :qdrant_url])
|> URI.parse()
|> Map.put(:path, "/healthz")
|> URI.to_string()
openai_health = Config.get([Pleroma.Search.QdrantSearch, :openai_healthcheck_url])
[qdrant_health, openai_health] |> Enum.filter(& &1)
end
end
defmodule Pleroma.Search.QdrantSearch.OpenAIClient do
use Tesla
alias Pleroma.Config.Getting, as: Config
plug(Tesla.Middleware.BaseUrl, Config.get([Pleroma.Search.QdrantSearch, :openai_url]))
plug(Tesla.Middleware.JSON)
plug(Tesla.Middleware.Headers, [
{"Authorization",
"Bearer #{Pleroma.Config.get([Pleroma.Search.QdrantSearch, :openai_api_key])}"}
])
end
defmodule Pleroma.Search.QdrantSearch.QdrantClient do
use Tesla
alias Pleroma.Config.Getting, as: Config
plug(Tesla.Middleware.BaseUrl, Config.get([Pleroma.Search.QdrantSearch, :qdrant_url]))
plug(Tesla.Middleware.JSON)
plug(Tesla.Middleware.Headers, [
{"api-key", Pleroma.Config.get([Pleroma.Search.QdrantSearch, :qdrant_api_key])}
])
end

File Metadata

Mime Type
text/x-diff
Expires
Sat, Aug 29, 2:58 AM (1 d, 7 h)
Storage Engine
blob
Storage Format
Raw Data
Storage Handle
1736764
Default Alt Text
(11 KB)

Event Timeline