OCI Generative AIを使用した会話型検索
OCI Generative AIコネクタを使用して、OpenSearchを使用したOCI SearchでエンドツーエンドのRetrieval-Augmented Generation (RAG)パイプラインを設定および使用するには、このウォークスルー内のステップに従います。
コネクタを利用して、Retrieval-Augmented Generation (RAG)、テキスト要約、テキスト生成、会話型検索、セマンティック検索など、すべての生成AI機能にアクセスできます。
生成AIコネクタの作成に必要な次のステップ:
これらの基本ステップに加えて、このトピックでは、OCI生成AIコネクタを使用して、OpenSearchを使用してOCI SearchでエンドツーエンドのRetrieval-Augmented Generation (RAG)パイプラインを設定および使用するために必要なステップについて説明します。各ステップには、必要なコードの汎用テンプレートが含まれています。コンソールを使用して、環境に構成された値を使用してこのコードを自動的に生成できます。「OpenSearchを使用した検索用のRAGパイプラインの作成」を参照してください。
コネクタは、生成AIがホストするCohere埋込みモデルを使用します。生成AIでは、Llma2モデルもサポートされており、これも試すことができます。
前提条件
- OCI生成AIを使用するには、テナンシが米国中西部(シカゴ)リージョンまたはドイツ中央部(フランクフルト)リージョンにサブスクライブされている必要があります。これらのリージョンのいずれかにクラスタを作成する必要はありません。テナンシがいずれかのリージョンにサブスクライブされていることを確認してください。
-
OCI SearchでOpenSearchを使用してOCI生成AIコネクタを使用するには、OpenSearchバージョン2.11を使用するように構成されたクラスタが必要です。デフォルトでは、新しいクラスタはバージョン2.11を使用するように構成されています。クラスタを作成するには、「OpenSearchクラスタの作成」を参照してください。
バージョン2.3に構成された既存のクラスタでは、バージョン2.11へのインライン・アップグレードを実行できます。詳細は、OpenSearchクラスタ・ソフトウェアのアップグレードを参照してください。
バージョン1.2.3用に構成された既存のクラスタを2.11にアップグレードするには、OpenSearchクラスタ・ソフトウェアのアップグレードで説明されているアップグレード・プロセスを使用する必要があります。
- 生成AIリソースへのアクセス権を付与するポリシーを作成します。次のポリシーの例には、必要な権限が含まれています。
ALLOW ANY-USER to manage generative-ai-family in tenancy WHERE ALL {request.principal.type='opensearchcluster', request.resource.compartment.id='<cluster_compartment_id>'}
- クラスタAPIの設定操作を使用して、コネクタを作成できる推奨クラスタ設定を構成します。次の例は、推奨される設定を示しています。
PUT _cluster/settings { "persistent": { "plugins": { "ml_commons": { "only_run_on_ml_node": "false", "model_access_control_enabled": "true", "native_memory_threshold": "99", "rag_pipeline_feature_enabled": "true", "memory_feature_enabled": "true", "allow_registering_model_via_local_file": "true", "allow_registering_model_via_url": "true", "model_auto_redeploy.enable":"true", "model_auto_redeploy.lifetime_retry_times": 10 } } } }
モデル・グループの登録
次の例に示すように、モデル・グループAPIの登録操作を使用してモデル・グループを登録します。
POST /_plugins/_ml/model_groups/_register
{
"name": "public_model_group-emb",
"description": "This is a public model group"
}
レスポンスで返されたmodel_group_id
を書き留めます。
{
"model_group_id": "<model_group_ID>",
"status": "CREATED"
}
コネクターの作成
GenAIサービスでサポートされている任意のリモートLLMモデルへのコネクタを作成できます。ON-DEMANDには複数のモデルがホストされていますが、これらのモデルは非推奨になる場合があります。必要に応じて、DEDICATED GENAIモデル・エンドポイントを構成して使用できます。
ON-DEMANDモデルを使用している場合は、GenAIサービスからのモデル非推奨通知を最新の状態に保ち、サービスの中断の可能性を回避するために、必要に応じてコネクタを更新します。サポートされているモデルのリストから大規模言語モデルを選択するには、生成AIの事前トレーニング済基本モデルを参照してください。
DEDICATEDモデルを使用している場合は、次のペイロード例のservingType
パラメータをON-DEMANDからDEDICATEDに変更します。
次の各項では、CohereおよびLlamaモデル・クラスのペイロード・テンプレートを示します。
Cohere.CommandモデルのGenAIコネクタ・テンプレート
ペイロード内の次のプレースホルダの情報を指定します。
<connector_name>
: コネクタを識別する一意の名前を入力します。たとえば、cohere command-r-plus connector v01です。<connector_description>
: 30文字までのコネクタの短い説明を入力します。たとえば、GenAI cohere.command-r-plusモデルへのコネクタです。<compartment_OCID>
: OpenSearchクラスタが存在するコンパートメントのOCIDを入力します。<genai_cohere_model>
: 使用するCohereモデルの名前を入力します。たとえば、「cohere.command-r-plus」です。
POST _plugins/_ml/connectors/_create
{
"name": "<connector_name>",
"description": "<connector_description>",
"version": 2,
"protocol": "oci_sigv1",
"parameters": {
"endpoint": "inference.generativeai.us-chicago-1.oci.oraclecloud.com",
"auth_type": "resource_principal"
},
"credential": {
},
"actions": [
{
"action_type": "predict",
"method": "POST",
"url": "https://${parameters.endpoint}/20231130/actions/chat",
"request_body": "{\"compartmentId\":\"<compartment_OCID>\",\"servingMode\":{\"modelId\":\"<genai_cohere_model>\",\"servingType\":\"ON_DEMAND\"},\"chatRequest\":{\"message\":\"${parameters.prompt}\",\"maxTokens\":600,\"temperature\":1,\"frequencyPenalty\":0,\"presencePenalty\":0,\"topP\":0.75,\"topK\":0,\"isStream\":false,\"chatHistory\":[],\"apiFormat\":\"COHERE\"}}",
"post_process_function": "def text = params['chatResponse']['text'].replace('\n', '\\\\n').replace('\"','');\n return '{\"name\":\"response\",\"dataAsMap\":{\"inferenceResponse\":{\"generatedTexts\":[{\"text\":\"' + text + '\"}]}}}'"
}
]
}
GenAI Meta LLAMAモデルのコネクタ・テンプレート
ペイロード内の次のプレースホルダの情報を指定します。
<connector_name>
: コネクタを識別する一意の名前を入力します。たとえば、「meta-llama connector v1」です。<connector_description>
: 30文字までのコネクタの短い説明を入力します。たとえば、「My connector to GenAI meta.llama」です。<compartment_OCID>
: OpenSearchクラスタが存在するコンパートメントのOCIDを入力します。<genai_llama_model>
: 使用するLLAMAモデルの名前を入力します。たとえば、「meta-llama connector v1」です。
POST _plugins/_ml/connectors/_create
{
"name": "<connector_name>",
"description": "<connector_description>",
"version": 2,
"protocol": "oci_sigv1",
"parameters": {
"endpoint": "inference.generativeai.us-chicago-1.oci.oraclecloud.com",
"auth_type": "resource_principal"
},
"credential": {
},
"actions": [
{
"action_type": "predict",
"method": "POST",
"url": "https://${parameters.endpoint}/20231130/actions/chat",
"request_body": "{\"compartmentId\":\<compartment_OCID>\",\"servingMode\":{\"modelId\":\"<genai_llama_model>\",\"servingType\":\"ON_DEMAND\"},\"chatRequest\":{\"maxTokens\":600,\"temperature\":1,\"frequencyPenalty\":0,\"presencePenalty\":0,\"topP\":0.75,\"topK\":-1,\"isStream\":false,\"apiFormat\":\"GENERIC\",\"messages\":[{\"role\":\"USER\",\"content\":[{\"type\":\"TEXT\",\"text\":\"${parameters.prompt}\"}]}]}}",
"post_process_function": "def text = params['chatResponse']['choices'][0]['message']['content'][0]['text'].replace('\n', '\\\\n').replace('\"','');\n return '{\"name\":\"response\",\"dataAsMap\":{\"inferenceResponse\":{\"generatedTexts\":[{\"text\":\"' + text + '\"}]}}}'"
}
]
}
OpenAIモデルのGenAIコネクタ・テンプレート
次に、OpenAIモデルのGenAIコネクタ・テンプレートの例を示します。
4o/4o-mini
POST _plugins/_ml/connectors/_create
{
"name": "rag-connector",
"description": "OpenAI connector for RAG pipeline",
"version": 2,
"protocol": "oci_sigv1",
"parameters": {
"endpoint": "inference.generativeai.us-chicago-1.oci.oraclecloud.com",
"auth_type": "resource_principal"
},
"credential": {
},
"actions": [
{
"action_type": "predict",
"method": "POST",
"url": "https://${parameters.endpoint}/20231130/actions/chat",
"request_body": "{\"compartmentId\":\"<compartment_OCID>\",\"servingMode\":{\"modelId\":\"<MODEL NAME>\",\"servingType\":\"ON_DEMAND\"},\"chatRequest\":{\"maxCompletionTokens\":600,\"temperature\":0.5,\"frequencyPenalty\":0,\"presencePenalty\":0,\"topP\":1.0,\"isStream\":false,\"apiFormat\":\"GENERIC\",\"messages\":[{\"role\":\"USER\",\"content\":[{\"type\":\"TEXT\",\"text\":\"${parameters.prompt}\"}]}]}}",
"post_process_function": "def text = params['chatResponse']['choices'][0]['message']['content'][0]['text'].replace('\n', '\\\\n').replace('\"','');\n return '{\"name\":\"response\",\"dataAsMap\":{\"inferenceResponse\":{\"generatedTexts\":[{\"text\":\"' + text + '\"}]}}}'"
}
]
}
o3-mini/o1
POST _plugins/_ml/connectors/_create
{
"name": "o3-mini-rag-connector",
"description": "OpenAI o3-mini connector for RAG pipeline",
"version": 2,
"protocol": "oci_sigv1",
"parameters": {
"endpoint": "inference.generativeai.us-chicago-1.oci.oraclecloud.com",
"auth_type": "resource_principal"
},
"credential": {
},
"actions": [
{
"action_type": "predict",
"method": "POST",
"url": "https://${parameters.endpoint}/20231130/actions/chat",
"request_body": "{\"compartmentId\":\"<compartment_OCID>\",\"servingMode\":{\"modelId\":\"<MODEL_NAME>\",\"servingType\":\"ON_DEMAND\"},\"chatRequest\":{\"isStream\":false,\"apiFormat\":\"GENERIC\",\"reasoningEffort\":\"LOW\",\"messages\":[{\"role\":\"USER\",\"content\":[{\"type\":\"TEXT\",\"text\":\"${parameters.prompt}\"}]}]}}",
"post_process_function": "def text = params['chatResponse']['choices'][0]['message']['content'][0]['text'].replace('\n', '\\\\n').replace('\"','');\n return '{\"name\":\"response\",\"dataAsMap\":{\"inferenceResponse\":{\"generatedTexts\":[{\"text\":\"' + text + '\"}]}}}'"
}
]
}
モデルを登録する
次の例に示すように、生成AIコネクタを使用して、前のステップのコネクタIDおよびモデル・グループIDでリモート・モデルを登録します。
POST /_plugins/_ml/models/_register
{
"name": "oci-genai-embed-test",
"function_name": "remote",
"model_group_id": "<model_group_ID>",
"description": "test semantic",
"connector_id": "<connector_ID>"
}
モデルのデプロイ
次の例に示すように、前のステップのレスポンスで返されたモデルIDを使用してモデルをデプロイします。
POST /_plugins/_ml/models/<embedding_model_ID>/_deploy
RAGパイプラインの作成
次の例に示すように、前のステップのmodel_id
を使用してRAGパイプラインを作成します。
PUT /_search/pipeline/demo_rag_pipeline
{
"response_processors": [
{
"retrieval_augmented_generation": {
"tag": "genai_conversational_search_demo",
"description": "Demo pipeline for conversational search Using Genai Connector",
"model_id": "<llm_model_ID>",
"conversation_id": "<conversation_ID>",
"context_field_list": ["<text_field_name>"],
"system_prompt":"hepfull assistant",
"user_instructions":"generate concise answer"
}
}
]
}
検索索引の作成
RAGパイプラインの作成後、任意の索引に対してRAGおよび会話型検索を実行できます。また、事前トレーニング済モデルでデータ取込みパイプラインを活用して、取得の一部としてハイブリッド検索を使用することもできます。
k-NNプラグインなしで検索インデックスを作成する
この項では、取込みパイプラインを使用せずに索引を作成するステップについて説明します。
このオプションを使用して、埋込みせずにデータを作成します。
- 次の例に示すように、検索索引を作成します。
PUT /conversation-demo-index { "settings": { "index": { "number_of_shards": 1, "number_of_replicas": 0 } }, "mappings": { "properties": { "title": { "type": "text" }, "text": { "type": "text" } } } }
- 次の例に示すように、データを索引に収集します。
PUT /conversation-demo-index/_doc/1 { "text": "The emergence of resistance of bacteria to antibiotics is a common phenomenon. Emergence of resistance often reflects evolutionary processes that take place during antibiotic therapy. The antibiotic treatment may select for bacterial strains with physiologically or genetically enhanced capacity to survive high doses of antibiotics. Under certain conditions, it may result in preferential growth of resistant bacteria, while growth of susceptible bacteria is inhibited by the drug. For example, antibacterial selection for strains having previously acquired antibacterial-resistance genes was demonstrated in 1943 by the Luria–Delbrück experiment. Antibiotics such as penicillin and erythromycin, which used to have a high efficacy against many bacterial species and strains, have become less effective, due to the increased resistance of many bacterial strains." } GET /conversation-demo-index/_doc/1 PUT /conversation-demo-index/_doc/2 { "text": "The successful outcome of antimicrobial therapy with antibacterial compounds depends on several factors. These include host defense mechanisms, the location of infection, and the pharmacokinetic and pharmacodynamic properties of the antibacterial. A bactericidal activity of antibacterials may depend on the bacterial growth phase, and it often requires ongoing metabolic activity and division of bacterial cells. These findings are based on laboratory studies, and in clinical settings have also been shown to eliminate bacterial infection. Since the activity of antibacterials depends frequently on its concentration, in vitro characterization of antibacterial activity commonly includes the determination of the minimum inhibitory concentration and minimum bactericidal concentration of an antibacterial. To predict clinical outcome, the antimicrobial activity of an antibacterial is usually combined with its pharmacokinetic profile, and several pharmacological parameters are used as markers of drug efficacy." } PUT /conversation-demo-index/_doc/3 { "text": "Antibacterial antibiotics are commonly classified based on their mechanism of action, chemical structure, or spectrum of activity. Most target bacterial functions or growth processes. Those that target the bacterial cell wall (penicillins and cephalosporins) or the cell membrane (polymyxins), or interfere with essential bacterial enzymes (rifamycins, lipiarmycins, quinolones, and sulfonamides) have bactericidal activities. Those that target protein synthesis (macrolides, lincosamides and tetracyclines) are usually bacteriostatic (with the exception of bactericidal aminoglycosides). Further categorization is based on their target specificity. Narrow-spectrum antibacterial antibiotics target specific types of bacteria, such as Gram-negative or Gram-positive bacteria, whereas broad-spectrum antibiotics affect a wide range of bacteria. Following a 40-year hiatus in discovering new classes of antibacterial compounds, four new classes of antibacterial antibiotics have been brought into clinical use in the late 2000s and early 2010s: cyclic lipopeptides (such as daptomycin), glycylcyclines (such as tigecycline), oxazolidinones (such as linezolid), and lipiarmycins (such as fidaxomicin)" } PUT /conversation-demo-index/_doc/4 { "text": "The Desert Land Act of 1877 was passed to allow settlement of arid lands in the west and allotted 640 acres (2.6 km2) to settlers for a fee of $.25 per acre and a promise to irrigate the land. After three years, a fee of one dollar per acre would be paid and the land would be owned by the settler. This act brought mostly cattle and sheep ranchers into Montana, many of whom grazed their herds on the Montana prairie for three years, did little to irrigate the land and then abandoned it without paying the final fees. Some farmers came with the arrival of the Great Northern and Northern Pacific Railroads throughout the 1880s and 1890s, though in relatively small numbers" } PUT /conversation-demo-index/_doc/5 { "text": "In the early 1900s, James J. Hill of the Great Northern began promoting settlement in the Montana prairie to fill his trains with settlers and goods. Other railroads followed suit. In 1902, the Reclamation Act was passed, allowing irrigation projects to be built in Montana's eastern river valleys. In 1909, Congress passed the Enlarged Homestead Act that expanded the amount of free land from 160 to 320 acres (0.6 to 1.3 km2) per family and in 1912 reduced the time to prove up on a claim to three years. In 1916, the Stock-Raising Homestead Act allowed homesteads of 640 acres in areas unsuitable for irrigation. This combination of advertising and changes in the Homestead Act drew tens of thousands of homesteaders, lured by free land, with World War I bringing particularly high wheat prices. In addition, Montana was going through a temporary period of higher-than-average precipitation. Homesteaders arriving in this period were known as Honyockers, or scissorbills. Though the word honyocker, possibly derived from the ethnic slur hunyak, was applied in a derisive manner at homesteaders as being greenhorns, new at his business or unprepared, the reality was that a majority of these new settlers had previous farming experience, though there were also many who did not" } PUT /conversation-demo-index/_doc/6 { "text": "In June 1917, the U.S. Congress passed the Espionage Act of 1917 which was later extended by the Sedition Act of 1918, enacted in May 1918. In February 1918, the Montana legislature had passed the Montana Sedition Act, which was a model for the federal version. In combination, these laws criminalized criticism of the U.S. government, military, or symbols through speech or other means. The Montana Act led to the arrest of over 200 individuals and the conviction of 78, mostly of German or Austrian descent. Over 40 spent time in prison. In May 2006, then-Governor Brian Schweitzer posthumously issued full pardons for all those convicted of violating the Montana Sedition Act." } PUT /conversation-demo-index/_doc/7 { "text": "When the U.S. entered World War II on December 8, 1941, many Montanans already had enlisted in the military to escape the poor national economy of the previous decade. Another 40,000-plus Montanans entered the armed forces in the first year following the declaration of war, and over 57,000 joined up before the war ended. These numbers constituted about 10 percent of the state's total population, and Montana again contributed one of the highest numbers of soldiers per capita of any state. Many Native Americans were among those who served, including soldiers from the Crow Nation who became Code Talkers. At least 1500 Montanans died in the war. Montana also was the training ground for the First Special Service Force or Devil's Brigade a joint U.S-Canadian commando-style force that trained at Fort William Henry Harrison for experience in mountainous and winter conditions before deployment. Air bases were built in Great Falls, Lewistown, Cut Bank and Glasgow, some of which were used as staging areas to prepare planes to be sent to allied forces in the Soviet Union. During the war, about 30 Japanese balloon bombs were documented to have landed in Montana, though no casualties nor major forest fires were attributed to them" }
このプロシージャでは、この索引で取込みパイプラインが使用されないため、取込み中にテキスト・ドキュメントに対して埋込みは生成されません。これは、関連するドキュメントを取得するためにBM25検索のみが使用されることを意味します。
k-NNプラグインなしで検索索引を作成した後、次のコマンドを実行して索引付きドキュメントをチェックすると、次のようにテキストのみが返されます。
要求:
GET /conversation-demo-index/_doc/1
レスポンス:
{
"_index": "conversation-demo-index",
"_id": "1",
"_version": 1,
"_seq_no": 0,
"_primary_term": 1,
"found": true,
"_source": {
"text": "The emergence of resistance of bacteria to antibiotics is a common phenomenon. Emergence of resistance often reflects evolutionary processes that take place during antibiotic therapy. The antibiotic treatment may select for bacterial strains with physiologically or genetically enhanced capacity to survive high doses of antibiotics. Under certain conditions, it may result in preferential growth of resistant bacteria, while growth of susceptible bacteria is inhibited by the drug. For example, antibacterial selection for strains having previously acquired antibacterial-resistance genes was demonstrated in 1943 by the Luria–Delbrück experiment. Antibiotics such as penicillin and erythromycin, which used to have a high efficacy against many bacterial species and strains, have become less effective, due to the increased resistance of many bacterial strains."
}
}
k-NNプラグインによる検索索引の作成
BM25のかわりにハイブリッド検索を利用してRAGパイプラインのリトリバー部分をエンリッチするには、取込みパイプラインを設定し、インポートされた事前トレーニング済モデルを使用して、取込み時にドキュメント埋込みが作成されるようにする必要があります。
このオプションを使用して、取込みパイプラインを含む索引を作成し、取込み中にデータの埋込みを自動的に生成します。
- このウォークスルーでは、次のいずれかのオプションを使用します。
-
オプション1: 「OpenSearch事前トレーニング済モデルの使用」で説明されているステップを使用して、OCI Searchでホストされている事前トレーニング済モデルをOpenSearchに登録してデプロイします。このオプションは最も簡単に使用でき、追加のIAMポリシーを構成する必要はなく、ペイロードは次のオプションのペイロードほど複雑ではありません。
-
オプション2: カスタム・モデルで説明されているステップを使用して、OpenSearch事前トレーニング済モデルをインポート、登録およびデプロイします。これには、オブジェクト・ストレージ・バケットへのモデル・ファイルのアップロード、およびモデルの登録時にモデル・ファイルのオブジェクト・ストレージURLの指定が含まれます。
-
オプション3: GenAIコネクタを使用して、リモートのGenAI埋込みモデル(cohere.embed-english-v3.0など)をクラスタに登録およびデプロイすることもできます。最初にコネクタを作成し、次のステップの説明に従ってコネクタIDを使用してモデルを登録およびデプロイする必要があります。
ノート
ON-DEMANDモデルを使用している場合は、GenAIサービスからのモデル非推奨通知を最新の状態に保ち、サービスの中断の可能性を回避するために、必要に応じてコネクタを更新します。サポートされている埋込みモデルで、サポートされているモデルのリストから埋込みモデルを選択するには、生成AIの事前トレーニング済基本モデルを参照してください。
DEDICATEDモデルを使用している場合は、次のペイロード例の
servingType
パラメータをON-DEMANDからDEDICATEDに変更します。
モデルの登録およびデプロイ時に返されたモデルIDを書き留めます。
-
- 次の例に示すように、前のステップの
model id
を使用して取込みパイプラインを作成します。PUT _ingest/pipeline/minil12-test-pipeline { "description": "pipeline for RAG demo index", "processors" : [ { "text_embedding": { "model_id": "<embedding_model_ID>", "field_map": { "text": "passage_embedding" } } } ] }
- 次の例に示すように、取込みパイプラインを使用して検索索引を作成します。
PUT /conversation-demo-index-knn { "settings": { "index.knn": true, "default_pipeline": "minil12-test-pipeline" }, "mappings": { "properties": { "passage_embedding": { "type": "knn_vector", "dimension": <model_dimension>, "method": { "name":"hnsw", "engine":"lucene", "space_type": "l2", "parameters":{ "m":512, "ef_construction": 245 } } }, "text": { "type": "text" } } } }
-
次の例に示すように、前のステップの取込みパイプラインを使用してデータを取り込みます。
PUT /conversation-demo-index-knn/_doc/1 { "text": "The emergence of resistance of bacteria to antibiotics is a common phenomenon. Emergence of resistance often reflects evolutionary processes that take place during antibiotic therapy. The antibiotic treatment may select for bacterial strains with physiologically or genetically enhanced capacity to survive high doses of antibiotics. Under certain conditions, it may result in preferential growth of resistant bacteria, while growth of susceptible bacteria is inhibited by the drug. For example, antibacterial selection for strains having previously acquired antibacterial-resistance genes was demonstrated in 1943 by the Luria–Delbrück experiment. Antibiotics such as penicillin and erythromycin, which used to have a high efficacy against many bacterial species and strains, have become less effective, due to the increased resistance of many bacterial strains." } GET /conversation-demo-index-knn/_doc/1 PUT /conversation-demo-index-knn/_doc/2 { "text": "The successful outcome of antimicrobial therapy with antibacterial compounds depends on several factors. These include host defense mechanisms, the location of infection, and the pharmacokinetic and pharmacodynamic properties of the antibacterial. A bactericidal activity of antibacterials may depend on the bacterial growth phase, and it often requires ongoing metabolic activity and division of bacterial cells. These findings are based on laboratory studies, and in clinical settings have also been shown to eliminate bacterial infection. Since the activity of antibacterials depends frequently on its concentration, in vitro characterization of antibacterial activity commonly includes the determination of the minimum inhibitory concentration and minimum bactericidal concentration of an antibacterial. To predict clinical outcome, the antimicrobial activity of an antibacterial is usually combined with its pharmacokinetic profile, and several pharmacological parameters are used as markers of drug efficacy." } PUT /conversation-demo-index-knn/_doc/3 { "text": "Antibacterial antibiotics are commonly classified based on their mechanism of action, chemical structure, or spectrum of activity. Most target bacterial functions or growth processes. Those that target the bacterial cell wall (penicillins and cephalosporins) or the cell membrane (polymyxins), or interfere with essential bacterial enzymes (rifamycins, lipiarmycins, quinolones, and sulfonamides) have bactericidal activities. Those that target protein synthesis (macrolides, lincosamides and tetracyclines) are usually bacteriostatic (with the exception of bactericidal aminoglycosides). Further categorization is based on their target specificity. Narrow-spectrum antibacterial antibiotics target specific types of bacteria, such as Gram-negative or Gram-positive bacteria, whereas broad-spectrum antibiotics affect a wide range of bacteria. Following a 40-year hiatus in discovering new classes of antibacterial compounds, four new classes of antibacterial antibiotics have been brought into clinical use in the late 2000s and early 2010s: cyclic lipopeptides (such as daptomycin), glycylcyclines (such as tigecycline), oxazolidinones (such as linezolid), and lipiarmycins (such as fidaxomicin)" } PUT /conversation-demo-index-knn/_doc/4 { "text": "The Desert Land Act of 1877 was passed to allow settlement of arid lands in the west and allotted 640 acres (2.6 km2) to settlers for a fee of $.25 per acre and a promise to irrigate the land. After three years, a fee of one dollar per acre would be paid and the land would be owned by the settler. This act brought mostly cattle and sheep ranchers into Montana, many of whom grazed their herds on the Montana prairie for three years, did little to irrigate the land and then abandoned it without paying the final fees. Some farmers came with the arrival of the Great Northern and Northern Pacific Railroads throughout the 1880s and 1890s, though in relatively small numbers" } PUT /conversation-demo-index-knn/_doc/5 { "text": "In the early 1900s, James J. Hill of the Great Northern began promoting settlement in the Montana prairie to fill his trains with settlers and goods. Other railroads followed suit. In 1902, the Reclamation Act was passed, allowing irrigation projects to be built in Montana's eastern river valleys. In 1909, Congress passed the Enlarged Homestead Act that expanded the amount of free land from 160 to 320 acres (0.6 to 1.3 km2) per family and in 1912 reduced the time to prove up on a claim to three years. In 1916, the Stock-Raising Homestead Act allowed homesteads of 640 acres in areas unsuitable for irrigation. This combination of advertising and changes in the Homestead Act drew tens of thousands of homesteaders, lured by free land, with World War I bringing particularly high wheat prices. In addition, Montana was going through a temporary period of higher-than-average precipitation. Homesteaders arriving in this period were known as Honyockers, or scissorbills. Though the word honyocker, possibly derived from the ethnic slur hunyak, was applied in a derisive manner at homesteaders as being greenhorns, new at his business or unprepared, the reality was that a majority of these new settlers had previous farming experience, though there were also many who did not" } PUT /conversation-demo-index-knn/_doc/6 { "text": "In June 1917, the U.S. Congress passed the Espionage Act of 1917 which was later extended by the Sedition Act of 1918, enacted in May 1918. In February 1918, the Montana legislature had passed the Montana Sedition Act, which was a model for the federal version. In combination, these laws criminalized criticism of the U.S. government, military, or symbols through speech or other means. The Montana Act led to the arrest of over 200 individuals and the conviction of 78, mostly of German or Austrian descent. Over 40 spent time in prison. In May 2006, then-Governor Brian Schweitzer posthumously issued full pardons for all those convicted of violating the Montana Sedition Act." } PUT /conversation-demo-index-knn/_doc/7 { "text": "When the U.S. entered World War II on December 8, 1941, many Montanans already had enlisted in the military to escape the poor national economy of the previous decade. Another 40,000-plus Montanans entered the armed forces in the first year following the declaration of war, and over 57,000 joined up before the war ended. These numbers constituted about 10 percent of the state's total population, and Montana again contributed one of the highest numbers of soldiers per capita of any state. Many Native Americans were among those who served, including soldiers from the Crow Nation who became Code Talkers. At least 1500 Montanans died in the war. Montana also was the training ground for the First Special Service Force or Devil's Brigade a joint U.S-Canadian commando-style force that trained at Fort William Henry Harrison for experience in mountainous and winter conditions before deployment. Air bases were built in Great Falls, Lewistown, Cut Bank and Glasgow, some of which were used as staging areas to prepare planes to be sent to allied forces in the Soviet Union. During the war, about 30 Japanese balloon bombs were documented to have landed in Montana, though no casualties nor major forest fires were attributed to them" }
k-NNプラグインを使用して検索索引を作成した後、次のコマンドを実行して索引付きドキュメントをチェックすると、レスポンスに次のように埋込みが含まれます。
要求:
GET /conversation-demo-index-knn/_doc/1
レスポンス:
{
"_index": "conversation-demo-index-knn",
"_id": "1",
"_version": 1,
"_seq_no": 0,
"_primary_term": 1,
"found": true,
"_source": {
"passage_embedding": [
-0.02929831,
-0.04421867,
-0.10647401,
0.07105031,
0.004921746,
-0.04529944,
-0.092778176,
0.14189903,
-0.0016610072,
0.08001712,
0.053442925,
-0.022703059,
0.039608333,
0.042299673,
..............
会話IDの作成
次のコマンドを実行して、会話IDを作成します:
POST /_plugins/_ml/memory/conversation
{
"name": "rag-conversation"
}
レスポンス:
{
"conversation_id": "<conversation_ID>"
}
BM25を使用してRAGを実行します
ドキュメントが索引付けされたら、次の例に示すように、「RAGパイプラインの作成」で指定されたRAGパイプラインの名前を使用してRAGを実行できます。
データ・サイエンス・コネクタを使用している場合は、"llm_model"
値を"oci_datascience/<your_llm_model_name>"
に変更する必要があります。
GET /conversation-demo-index/_search?search_pipeline=<pipeline_name>
{
"query": {
"match": {
"text": {
"query": "when did us pass espionage act?"
}
}
},
"ext": {
"generative_qa_parameters": {
"llm_model": "oci_genai/<your_llm_model_name>",
"llm_question": "when did us pass espionage act? answer only in two sentences using provided context.",
"conversation_id": "<conversation_ID>",
"context_size": 2,
"interaction_size": 1,
"timeout": 15
}
}
}
最初の部分は、ユーザーの問合せに基づいて最も関連性の高いドキュメントを見つけるための索引への問合せによる取得です。2番目の部分では、より多くの命令でユーザー問合せが拡張され、取得部分からのレスポンスがコンテキストとして使用されます。これらはすべて、ユースケース・データのナレッジのみを使用して回答を生成するために、大規模言語モデルに渡されます。
<your_llm_model_name>
の「コネクタの作成」から、ペイロードで使用したモデル名を指定します。モデル名の例を次に示します。
oci_genai/cohere.command-r-plus-08-2024
oci_genai/cohere.command-08-2024
oci_genai/meta.llama-3.1-70b-instruct
oci_genai/meta.llama-3.2-90b-vision-instruct
次のレスポンスでは、最初の部分は、リトリーバ(OpenSearchの検索エンジン)によって返される一連のドキュメントです。この後に、大規模言語モデル(LLM)の回答が続きます。これは、LLMのナレッジ・ベースを強化するために、テキスト生成とコンテキスト内学習を使用したLLMモデルからの実際のレスポンスです。ここで使用される検索エンジンはBM25です。これは、conversation-demo-index
索引が、取込み中にデプロイされたモデルを使用してドキュメント埋込みを生成しないためです。
{
"took": 1,
"timed_out": false,
"_shards": {
"total": 1,
"successful": 1,
"skipped": 0,
"failed": 0
},
"hits": {
"total": {
"value": 4,
"relation": "eq"
},
"max_score": 3.6364775,
"hits": [
{
"_index": "conversation-demo-index",
"_id": "6",
"_score": 3.6364775,
"_source": {
"text": "In June 1917, the U.S. Congress passed the Espionage Act of 1917 which was later extended by the Sedition Act of 1918, enacted in May 1918. In February 1918, the Montana legislature had passed the Montana Sedition Act, which was a model for the federal version. In combination, these laws criminalized criticism of the U.S. government, military, or symbols through speech or other means. The Montana Act led to the arrest of over 200 individuals and the conviction of 78, mostly of German or Austrian descent. Over 40 spent time in prison. In May 2006, then-Governor Brian Schweitzer posthumously issued full pardons for all those convicted of violating the Montana Sedition Act."
}
},
{
"_index": "conversation-demo-index",
"_id": "4",
"_score": 2.675274,
"_source": {
"text": "The Desert Land Act of 1877 was passed to allow settlement of arid lands in the west and allotted 640 acres (2.6 km2) to settlers for a fee of $.25 per acre and a promise to irrigate the land. After three years, a fee of one dollar per acre would be paid and the land would be owned by the settler. This act brought mostly cattle and sheep ranchers into Montana, many of whom grazed their herds on the Montana prairie for three years, did little to irrigate the land and then abandoned it without paying the final fees. Some farmers came with the arrival of the Great Northern and Northern Pacific Railroads throughout the 1880s and 1890s, though in relatively small numbers"
}
},
{
"_index": "conversation-demo-index",
"_id": "5",
"_score": 2.5380564,
"_source": {
"text": "In the early 1900s, James J. Hill of the Great Northern began promoting settlement in the Montana prairie to fill his trains with settlers and goods. Other railroads followed suit. In 1902, the Reclamation Act was passed, allowing irrigation projects to be built in Montana's eastern river valleys. In 1909, Congress passed the Enlarged Homestead Act that expanded the amount of free land from 160 to 320 acres (0.6 to 1.3 km2) per family and in 1912 reduced the time to prove up on a claim to three years. In 1916, the Stock-Raising Homestead Act allowed homesteads of 640 acres in areas unsuitable for irrigation. This combination of advertising and changes in the Homestead Act drew tens of thousands of homesteaders, lured by free land, with World War I bringing particularly high wheat prices. In addition, Montana was going through a temporary period of higher-than-average precipitation. Homesteaders arriving in this period were known as Honyockers, or scissorbills. Though the word honyocker, possibly derived from the ethnic slur hunyak, was applied in a derisive manner at homesteaders as being greenhorns, new at his business or unprepared, the reality was that a majority of these new settlers had previous farming experience, though there were also many who did not"
}
},
{
"_index": "conversation-demo-index",
"_id": "7",
"_score": 1.4905708,
"_source": {
"text": "When the U.S. entered World War II on December 8, 1941, many Montanans already had enlisted in the military to escape the poor national economy of the previous decade. Another 40,000-plus Montanans entered the armed forces in the first year following the declaration of war, and over 57,000 joined up before the war ended. These numbers constituted about 10 percent of the state's total population, and Montana again contributed one of the highest numbers of soldiers per capita of any state. Many Native Americans were among those who served, including soldiers from the Crow Nation who became Code Talkers. At least 1500 Montanans died in the war. Montana also was the training ground for the First Special Service Force or Devil's Brigade a joint U.S-Canadian commando-style force that trained at Fort William Henry Harrison for experience in mountainous and winter conditions before deployment. Air bases were built in Great Falls, Lewistown, Cut Bank and Glasgow, some of which were used as staging areas to prepare planes to be sent to allied forces in the Soviet Union. During the war, about 30 Japanese balloon bombs were documented to have landed in Montana, though no casualties nor major forest fires were attributed to them"
}
}
]
},
"ext": {
"retrieval_augmented_generation": {
"answer": " Through the Espionage Act of 1917 and the Sedition Act of 1918, passed in May of 1918, the U.S. Congress outlawed criticism of the military, government, or symbols through speech or other means. The Montana Sedition Act was enacted in February 1918, serving as a model for the federal version, and resulting in the arrest of over 200 people, chiefly of German or Austrian descent, with over 40 imprisoned. "
}
}
}
ハイブリッド検索を使用したRAGの実行
また、レトリバーとしてハイブリッド検索でRAGを実行することもできます。BM25のかわりにハイブリッド検索を使用すると、リトリーバの品質を大幅に改善できます。これは、ハイブリッド検索リトリーバがデプロイされたモデルを使用して、ユーザー問合せを索引付けされたドキュメントと同じハイパースペースに埋め込み、純粋なセマンティック検索を実行して最も関連性の高いドキュメントを取得し、LLMの知識を強化するためです。リトライバーがLLMに最も関連性の高いコンテキストを取得して提供するのに良い仕事をしない場合、LLMモデルの応答はそれほど正確ではありません。
デプロイ済の事前トレーニング済センテンス・トランスフォーマ・モデルを含む取込みパイプラインをすでに使用している「検索索引の作成」のconversation-demo-index-knn
索引を使用して、RAG問合せでは、次の例に示すように、BM5検索のかわりにハイブリッド検索が使用されます。
GET /conversation-demo-index-knn/_search?search_pipeline=<pipeline_name>
{
"query": {
"bool" : {
"should" : [
{
"script_score": {
"query": {
"neural": {
"passage_embedding": {
"query_text": "when did us pass espionage act?",
"model_id": "<embedding_model_ID>",
"k": 3
}
}
},
"script": {
"source": "_score * 1.5"
}
}
}
]
}
},
"ext": {
"generative_qa_parameters": {
"llm_model": "oci_genai/<your_llm_model_name>",
"llm_question": "when did us pass espionage act? answer only in two sentences using provided context.",
"context_size": 2,
"interaction_size": 1,
"timeout": 15
}
}
}
<your_llm_model_name>
の「コネクタの作成」から、ペイロードで使用したモデル名を指定します。モデル名の例を次に示します。
oci_genai/cohere.command-r-plus-08-2024
oci_genai/cohere.command-08-2024
oci_genai/meta.llama-3.1-70b-instruct
oci_genai/meta.llama-3.2-90b-vision-instruct
データ・サイエンス・コネクタを使用している場合は、"llm_model"
値を"oci_datascience/<your_llm_model_name>"
に変更する必要があります。
レスポンス:
{
"took": 1,
"timed_out": false,
"_shards": {
"total": 1,
"successful": 1,
"skipped": 0,
"failed": 0
},
"hits": {
"total": {
"value": 3,
"relation": "eq"
},
"max_score": 0.80985546,
"hits": [
{
"_index": "conversation-demo-index-knn",
"_id": "6",
"_score": 0.80985546,
"_source": {
"passage_embedding": [
-0.015252565,
0.023013491,
-0.023333456,
-0.088787265,
0.03142115,
0.053571254,
0.067729644,
-0.018526044,
-0.02262757,
0.054774728,
0.095119946,
.......
],
"text": "In June 1917, the U.S. Congress passed the Espionage Act of 1917 which was later extended by the Sedition Act of 1918, enacted in May 1918. In February 1918, the Montana legislature had passed the Montana Sedition Act, which was a model for the federal version. In combination, these laws criminalized criticism of the U.S. government, military, or symbols through speech or other means. The Montana Act led to the arrest of over 200 individuals and the conviction of 78, mostly of German or Austrian descent. Over 40 spent time in prison. In May 2006, then-Governor Brian Schweitzer posthumously issued full pardons for all those convicted of violating the Montana Sedition Act."
}
},
{
"_index": "conversation-demo-index-knn",
"_id": "7",
"_score": 0.5822973,
"_source": {
"passage_embedding": [
0.016897075,
-0.027237555,
-0.026178025,
-0.041597113,
-0.07700658,
0.02490874,
0.009785392,
........
],
"text": "When the U.S. entered World War II on December 8, 1941, many Montanans already had enlisted in the military to escape the poor national economy of the previous decade. Another 40,000-plus Montanans entered the armed forces in the first year following the declaration of war, and over 57,000 joined up before the war ended. These numbers constituted about 10 percent of the state's total population, and Montana again contributed one of the highest numbers of soldiers per capita of any state. Many Native Americans were among those who served, including soldiers from the Crow Nation who became Code Talkers. At least 1500 Montanans died in the war. Montana also was the training ground for the First Special Service Force or Devil's Brigade a joint U.S-Canadian commando-style force that trained at Fort William Henry Harrison for experience in mountainous and winter conditions before deployment. Air bases were built in Great Falls, Lewistown, Cut Bank and Glasgow, some of which were used as staging areas to prepare planes to be sent to allied forces in the Soviet Union. During the war, about 30 Japanese balloon bombs were documented to have landed in Montana, though no casualties nor major forest fires were attributed to them"
}
},
{
"_index": "conversation-demo-index-knn",
"_id": "4",
"_score": 0.58108574,
"_source": {
"passage_embedding": [
0.017924132,
0.03570767,
0.024848921,
-0.023073182,
-0.0023820316,
0.009969,
0.076653704,
-0.10182037,
.......
],
"text": "The Desert Land Act of 1877 was passed to allow settlement of arid lands in the west and allotted 640 acres (2.6 km2) to settlers for a fee of $.25 per acre and a promise to irrigate the land. After three years, a fee of one dollar per acre would be paid and the land would be owned by the settler. This act brought mostly cattle and sheep ranchers into Montana, many of whom grazed their herds on the Montana prairie for three years, did little to irrigate the land and then abandoned it without paying the final fees. Some farmers came with the arrival of the Great Northern and Northern Pacific Railroads throughout the 1880s and 1890s, though in relatively small numbers"
}
}
]
},
"ext": {
"retrieval_augmented_generation": {
"answer": """ The United States passed the Espionage Act in 1917, with the Sedition Act being enacted in 1918. This was preceded by the Montana Sedition act in 1918, which served as a model for the federal version, and resulted in the arrest of over 200 people, many of German or Austrian descent.
Would you like to know more about the Espionage act or any other events that occurred during that period? """
}
}
}
会話検索の実行
会話型検索を実行するには、会話メモリーを作成し、返された会話IDをRAG APIコールに渡します。これらの例のモデル名について、「コネクタの作成」のペイロードで使用したモデル名を指定し、<llm_model_name>
をモデル名に置き換えます。モデル名の例を次に示します。
oci_genai/cohere.command-r-plus-08-2024
oci_genai/cohere.command-08-2024
oci_genai/meta.llama-3.1-70b-instruct
oci_genai/meta.llama-3.2-90b-vision-instruct
次の例は、会話IDを取得するための会話メモリーの作成方法を示しています。
POST /_plugins/_ml/memory/conversation
{
"name": "rag-conversation"
}
レスポンス:
{
"conversation_id": "<conversation_ID>"
}
BM25 Retrieverを使用した会話型検索
GET /conversation-demo-index/_search?search_pipeline=<pipeline_name>
{
"query": {
"match": {
"text": {
"query": "when did us pass espionage act?"
}
}
},
"ext": {
"generative_qa_parameters": {
"llm_model": "oci_genai/<your_llm_model_name>",
"llm_question": "when did us pass espionage act? answer only in two sentences using provided context.",
"conversation_id": "<conversation_ID>",
"context_size": 2,
"interaction_size": 1,
"timeout": 15
}
}
}
ハイブリッド検索リトリーバによる会話検索
GET /conversation-demo-index-knn/_search?search_pipeline=<pipeline_name>
{
"query": {
"bool" : {
"should" : [
{
"script_score": {
"query": {
"neural": {
"passage_embedding": {
"query_text": "when did us pass espionage act?",
"model_id": "<embedding_model_ID>",
"k": 3
}
}
},
"script": {
"source": "_score * 1.5"
}
}
}
]
}
},
"ext": {
"generative_qa_parameters": {
"llm_model": "oci_genai/<your_llm_model_name>",
"llm_question": "when did us pass espionage act? answer only in two sentences using provided context.",
"conversation_id": "<conversation_ID>",
"context_size": 2,
"interaction_size": 1,
"timeout": 15
}
}
}
<your_llm_model_name>
には、使用するモデルの名前を指定します。たとえば: oci_genai/cohere.command-r-plus-08-2024
oci_genai/cohere.command-08-2024
oci_genai/meta.llama-3.1-70b-instruct
oci_genai/meta.llama-3.2-90b-vision-instruct
会話IDを指定すると、OpenSearchに、会話の履歴を追跡するためのメモリーを作成するように求められます。次の詳細が、会話型検索のためにLLMに渡されます。
- 取得されたコンテキスト・ドキュメント。
- ユーザーの入力問合せおよびプロンプトのファインチューニング。
- 指定した会話IDに基づくユーザーの以前の会話履歴。
APIコールでinteraction_size
パラメータを使用して、考慮する以前の会話コンテキストの数を制御できます。context_size
を使用して、LLMに解析する取得済最上位ドキュメントの数をコンテキストとして制御し、ナレッジを強化することもできます。