[vector-databases] Add support for Apache Solr (#565)

examples/applications/query-solr/.gitignore

@@ -0,0 +1 @@
+java/lib/*

examples/applications/query-solr/README.md

@@ -0,0 +1,60 @@
+# Indexing a WebSite using Apache Solr as Vector Database
+
+This sample application shows how to use the WebCrawler Source Connector and use [Apache Solr](https://solr.apache.org) as a Vector Database.
+
+## Prerequisites
+
+Launch Apache Solr locally in docker
+
+```
+docker run --rm  -p 8983:8983 --rm solr:9.3.0 -c
+```
+
+You can now open your browser at http://localhost:8983/ and you will see the Solr admin page.
+
+The '-c' parameter launches Solr in "Cloud" mode, that allows you to dynamically create collections.
+
+
+The LangStream application will create for you a collection named "documents".
+
+It create a new data type "vector" following this guide:
+https://solr.apache.org/guide/solr/latest/query-guide/dense-vector-search.html
+
+## Configure access to the Vector Database
+
+In order to allow LangStream that runs in docker to connect to the Solr instance running in your host, you need to configure the SOLR_HOST environment variable.
+
+```bash
+SOLR_HOST=host.docker.internal
+```
+
+
+The examples/secrets/secrets.yaml resolves environment variables for you.
+When you go in production you are supposed to create a dedicated secrets.yaml file for each environment.
+
+
+## Configure the pipeline
+
+Edit the file `crawler.yaml` and configure the list of the allowed web domains, this is required in order to not let the crawler escape outside your data.
+Configure the list of seed URLs, for instance with your home page.
+
+The default configuration in this example will crawl the LangStream website.
+
+## Run the LangStream application locally on docker
+
+```
+./bin/langstream docker run test -app examples/applications/query_solr  -s examples/secrets/secrets.yaml
+```
+
+## Talk with the Chat bot using the UI
+
+By default the langstream CLI opens a UI in your browser. You can use that to chat with the bot.
+
+## Talk with the Chat bot using the CLI
+Since the application opens a gateway, we can use the gateway API to send and consume messages.
+
+```
+./bin/langstream gateway chat test -cg bot-output -pg user-input -p sessionId=$(uuidgen)
+```
+
+

examples/applications/query-solr/chatbot.yaml

@@ -0,0 +1,91 @@
+#
+# Copyright DataStax, Inc.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+topics:
+  - name: "questions-topic"
+    creation-mode: create-if-not-exists
+  - name: "answers-topic"
+    creation-mode: create-if-not-exists
+  - name: "log-topic"
+    creation-mode: create-if-not-exists
+errors:
+    on-failure: "skip"
+pipeline:
+  - name: "convert-to-structure"
+    type: "document-to-json"
+    input: "questions-topic"
+    configuration:
+      text-field: "question"
+  - name: "compute-embeddings"
+    type: "compute-ai-embeddings"
+    configuration:
+      model: "${secrets.open-ai.embeddings-model}" # This needs to match the name of the model deployment, not the base model
+      embeddings-field: "value.question_embeddings"
+      text: "{{ value.question }}"
+      flush-interval: 0
+  - name: "lookup-related-documents"
+    type: "query-vector-db"
+    configuration:
+      datasource: "SolrDataSource"
+      query: |
+        {
+          "q": "{!knn f=embeddings topK=10}?"
+        }
+      fields:
+        - "fn:toListOfFloat(value.question_embeddings)"
+      output-field: "value.related_documents"
+  - name: "ai-chat-completions"
+    type: "ai-chat-completions"
+
+    configuration:
+      model: "${secrets.open-ai.chat-completions-model}" # This needs to be set to the model deployment name, not the base name
+      # on the log-topic we add a field with the answer
+      completion-field: "value.answer"
+      # we are also logging the prompt we sent to the LLM
+      log-field: "value.prompt"
+      # here we configure the streaming behavior
+      # as soon as the LLM answers with a chunk we send it to the answers-topic
+      stream-to-topic: "answers-topic"
+      # on the streaming answer we send the answer as whole message
+      # the 'value' syntax is used to refer to the whole value of the message
+      stream-response-completion-field: "value"
+      # we want to stream the answer as soon as we have 20 chunks
+      # in order to reduce latency for the first message the agent sends the first message
+      # with 1 chunk, then with 2 chunks....up to the min-chunks-per-message value
+      # eventually we want to send bigger messages to reduce the overhead of each message on the topic
+      min-chunks-per-message: 20
+      messages:
+        - role: system
+          content: |
+              An user is going to perform a questions, The documents below may help you in answering to their questions.
+              Please try to leverage them in your answer as much as possible.
+              Take into consideration that the user is always asking questions about the LangStream project.
+              If you provide code or YAML snippets, please explicitly state that they are examples.
+              Do not provide information that is not related to the LangStream project.
+            
+              Documents:
+              {{# value.related_documents}}
+              {{ text}}
+              {{/ value.related_documents}}
+        - role: user
+          content: "{{ value.question}}"
+  - name: "cleanup-response"
+    type: "drop-fields"
+    output: "log-topic"
+    configuration:
+      fields:
+        - "question_embeddings"
+        - "related_documents"

examples/applications/query-solr/configuration.yaml

@@ -0,0 +1,35 @@
+#
+#
+# Copyright DataStax, Inc.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+configuration:
+  resources:
+  - type: "open-ai-configuration"
+    name: "OpenAI Azure configuration"
+    configuration:
+      url: "${secrets.open-ai.url}"
+      access-key: "${secrets.open-ai.access-key}"
+      provider: "${secrets.open-ai.provider}"
+  - type: "vector-database"
+    name: "SolrDataSource"
+    configuration:
+      service: "solr"
+      user: "${secrets.solr.username}"
+      password: "${secrets.solr.password}"
+      host: "${secrets.solr.host}"
+      port: "${secrets.solr.port}"
+      collection-name: "documents"
+

examples/applications/query-solr/crawler.yaml

@@ -0,0 +1,154 @@
+#
+# Copyright DataStax, Inc.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+name: "Crawl a website"
+topics:
+  - name: "chunks-topic"
+    creation-mode: create-if-not-exists
+assets:
+  - name: "documents-table"
+    asset-type: "solr-collection"
+    creation-mode: create-if-not-exists
+    deletion-mode: delete
+    config:
+      collection-name: "documents"
+      datasource: "SolrDataSource"
+      create-statements:
+        - api: "/api/collections"
+          method: "POST"
+          body: |
+            {
+              "name": "documents",
+              "numShards": 1,
+              "replicationFactor": 1
+             }
+        - "api": "/schema"
+          "body": |
+            {
+             "add-field-type" : {
+                   "name": "knn_vector",
+                   "class": "solr.DenseVectorField",
+                   "vectorDimension": "1536",
+                   "similarityFunction": "cosine"
+              }
+             }
+
+        - "api": "/schema"
+          "body": |
+            {
+              "add-field":{
+                "name":"embeddings",
+                "type":"knn_vector",
+                "stored":true,
+                "indexed":true
+                }
+            }
+        - "api": "/schema"
+          "body": |
+            {
+               "add-field":{
+                   "name":"text",
+                   "type":"string",
+                   "stored":true,
+                   "indexed":false,
+                   "multiValued": false
+               }
+            }
+
+resources:
+      size: 1
+pipeline:
+  - name: "Crawl the WebSite"
+    type: "webcrawler-source"
+    configuration:
+      seed-urls: ["https://docs.langstream.ai/"]
+      allowed-domains: ["https://docs.langstream.ai"]
+      forbidden-paths: []
+      min-time-between-requests: 500
+      reindex-interval-seconds: 3600
+      max-error-count: 5
+      max-urls: 1000
+      max-depth: 50
+      handle-robots-file: true
+      user-agent: "" # this is computed automatically, but you can override it
+      scan-html-documents: true
+      http-timeout: 10000
+      handle-cookies: true
+      max-unflushed-pages: 100
+      bucketName: "${secrets.s3.bucket-name}"
+      endpoint: "${secrets.s3.endpoint}"
+      access-key: "${secrets.s3.access-key}"
+      secret-key: "${secrets.s3.secret}"
+      region: "${secrets.s3.region}"
+  - name: "Extract text"
+    type: "text-extractor"
+  - name: "Normalise text"
+    type: "text-normaliser"
+    configuration:
+      make-lowercase: true
+      trim-spaces: true
+  - name: "Detect language"
+    type: "language-detector"
+    configuration:
+      allowedLanguages: ["en", "fr"]
+      property: "language"
+  - name: "Split into chunks"
+    type: "text-splitter"
+    configuration:
+      splitter_type: "RecursiveCharacterTextSplitter"
+      chunk_size: 400
+      separators: ["\n\n", "\n", " ", ""]
+      keep_separator: false
+      chunk_overlap: 100
+      length_function: "cl100k_base"
+  - name: "Convert to structured data"
+    type: "document-to-json"
+    configuration:
+      text-field: text
+      copy-properties: true
+  - name: "prepare-structure"
+    type: "compute"
+    configuration:
+      fields:
+        - name: "value.filename"
+          expression: "properties.url"
+          type: STRING
+        - name: "value.chunk_id"
+          expression: "properties.chunk_id"
+          type: STRING
+  - name: "compute-embeddings"
+    id: "step1"
+    type: "compute-ai-embeddings"
+    output: chunks-topic
+    configuration:
+      model: "text-embedding-ada-002" # This needs to match the name of the model deployment, not the base model
+      embeddings-field: "value.embeddings_vector"
+      text: "{{ value.text }}"
+      batch-size: 10
+      flush-interval: 500
+  - name: "Write to Solr"
+    type: "vector-db-sink"
+    input: chunks-topic
+    configuration:
+      datasource: "SolrDataSource"
+      collection-name: "documents"
+      fields:
+        - name: "id"
+          expression: "fn:concat(value.filename, value.chunk_id)"
+        - name: "embeddings"
+          expression: "fn:toListOfFloat(value.embeddings_vector)"
+        - name: "text"
+          expression: "value.text"

examples/applications/query-solr/gateways.yaml

@@ -0,0 +1,43 @@
+#
+#
+# Copyright DataStax, Inc.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+gateways:
+  - id: "user-input"
+    type: produce
+    topic: "questions-topic"
+    parameters:
+      - sessionId
+    produceOptions:
+      headers:
+        - key: langstream-client-session-id
+          valueFromParameters: sessionId
+
+  - id: "bot-output"
+    type: consume
+    topic: "answers-topic"
+    parameters:
+      - sessionId
+    consumeOptions:
+      filters:
+        headers:
+          - key: langstream-client-session-id
+            valueFromParameters: sessionId
+
+
+  - id: "llm-debug"
+    type: consume
+    topic: "log-topic"