Release 0.3.6 (#810 )

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
chore: update package.json and usage of lodash (#809 )
2026-07-07 00:31:11 -04:00 · 2024-05-05 18:40:58 -05:00 · 2024-05-05 18:30:46 -05:00 · 2024-05-03 18:21:08 -05:00 · 2024-05-03 18:16:39 -05:00 · 2024-05-03 18:13:24 -05:00
44 changed files with 1822 additions and 101 deletions
@@ -1,5 +1,23 @@
 # docs

+## 0.0.14
+
+### Patch Changes
+
+- Updated dependencies [efa326a]
+  - llamaindex@0.3.6
+
+## 0.0.13
+
+### Patch Changes
+
+- Updated dependencies [bc7a11c]
+- Updated dependencies [2fe2b81]
+- Updated dependencies [5596e31]
+- Updated dependencies [e74fe88]
+- Updated dependencies [be5df5b]
+  - llamaindex@0.3.5
+
 ## 0.0.12

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "docs",
-  "version": "0.0.12",
+  "version": "0.0.14",
  "private": true,
  "scripts": {
    "docusaurus": "docusaurus",
@@ -15,7 +15,7 @@
    "release": "pnpm run check-minor-version && pnpm run build:release && changeset publish",
    "release-snapshot": "pnpm run check-minor-version && pnpm run build:release && changeset publish --tag snapshot",
    "check-minor-version": "node ./scripts/check-minor-version",
-    "new-version": "changeset version && pnpm run check-minor-version && pnpm run build:release",
+    "new-version": "changeset version && pnpm run check-minor-version && pnpm format:write && pnpm run build:release",
    "new-snapshot": "pnpm run build:release && changeset version --snapshot"
  },
  "devDependencies": {
@@ -1,5 +1,26 @@
 # llamaindex

+## 0.3.6
+
+### Patch Changes
+
+- efa326a: chore: update package.json
+- Updated dependencies [efa326a]
+- Updated dependencies [efa326a]
+  - @llamaindex/env@0.1.2
+
+## 0.3.5
+
+### Patch Changes
+
+- bc7a11c: fix: inline ollama build
+- 2fe2b81: fix: filter with multiple filters in ChromaDB
+- 5596e31: feat: improve `@llamaindex/env`
+- e74fe88: fix: change <-> to <=> in the SELECT query
+- be5df5b: fix: anthropic agent on multiple chat
+- Updated dependencies [5596e31]
+  - @llamaindex/env@0.1.1
+
 ## 0.3.4

 ### Patch Changes
@@ -1,5 +1,11 @@
 # @llamaindex/core-e2e

+## 0.0.4
+
+### Patch Changes
+
+- be5df5b: fix: anthropic agent on multiple chat
+
 ## 0.0.3

 ### Patch Changes
@@ -1,5 +1,23 @@
 # @llamaindex/cloudflare-worker-agent-test

+## 0.0.7
+
+### Patch Changes
+
+- Updated dependencies [efa326a]
+  - llamaindex@0.3.6
+
+## 0.0.6
+
+### Patch Changes
+
+- Updated dependencies [bc7a11c]
+- Updated dependencies [2fe2b81]
+- Updated dependencies [5596e31]
+- Updated dependencies [e74fe88]
+- Updated dependencies [be5df5b]
+  - llamaindex@0.3.5
+
 ## 0.0.5

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.5",
+  "version": "0.0.7",
  "type": "module",
  "private": true,
  "scripts": {
@@ -1,5 +1,23 @@
 # @llamaindex/next-agent-test

+## 0.1.7
+
+### Patch Changes
+
+- Updated dependencies [efa326a]
+  - llamaindex@0.3.6
+
+## 0.1.6
+
+### Patch Changes
+
+- Updated dependencies [bc7a11c]
+- Updated dependencies [2fe2b81]
+- Updated dependencies [5596e31]
+- Updated dependencies [e74fe88]
+- Updated dependencies [be5df5b]
+  - llamaindex@0.3.5
+
 ## 0.1.5

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/next-agent-test",
-  "version": "0.1.5",
+  "version": "0.1.7",
  "private": true,
  "scripts": {
    "dev": "next dev",
@@ -1,5 +1,17 @@
 # test-edge-runtime

+## 0.1.8
+
+### Patch Changes
+
+- @llamaindex/edge@0.3.6
+
+## 0.1.7
+
+### Patch Changes
+
+- @llamaindex/edge@0.3.5
+
 ## 0.1.6

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.6",
+  "version": "0.1.8",
  "private": true,
  "scripts": {
    "dev": "next dev",
@@ -1,5 +1,23 @@
 # @llamaindex/waku-query-engine-test

+## 0.0.7
+
+### Patch Changes
+
+- Updated dependencies [efa326a]
+  - llamaindex@0.3.6
+
+## 0.0.6
+
+### Patch Changes
+
+- Updated dependencies [bc7a11c]
+- Updated dependencies [2fe2b81]
+- Updated dependencies [5596e31]
+- Updated dependencies [e74fe88]
+- Updated dependencies [be5df5b]
+  - llamaindex@0.3.5
+
 ## 0.0.5

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.5",
+  "version": "0.0.7",
  "type": "module",
  "private": true,
  "scripts": {
@@ -4,7 +4,7 @@ import { AnthropicAgent } from "llamaindex/agent/anthropic";
 import { extractText } from "llamaindex/llm/utils";
 import { ok, strictEqual } from "node:assert";
 import { beforeEach, test } from "node:test";
-import { sumNumbersTool } from "./fixtures/tools.js";
+import { getWeatherTool, sumNumbersTool } from "./fixtures/tools.js";
 import { mockLLMEvent } from "./utils.js";

 let llm: LLM;
@@ -118,14 +118,58 @@ await test("anthropic agent", async (t) => {
  });

  await t.test("sum numbers", async () => {
-    const openaiAgent = new AnthropicAgent({
+    const anthropicAgent = new AnthropicAgent({
      tools: [sumNumbersTool],
    });

-    const { response } = await openaiAgent.chat({
+    const { response } = await anthropicAgent.chat({
      message: "how much is 1 + 1?",
    });

    ok(extractText(response.message.content).includes("2"));
  });
 });
+
+await test("anthropic agent with multiple chat", async (t) => {
+  await mockLLMEvent(t, "anthropic-agent-multiple-chat");
+  await t.test("chat", async () => {
+    const agent = new AnthropicAgent({
+      tools: [getWeatherTool],
+    });
+    {
+      const { response } = await agent.chat({
+        message: 'Hello? Response to me "Yes"',
+      });
+      consola.debug("response:", response.message.content);
+      ok(extractText(response.message.content).includes("Yes"));
+    }
+    {
+      const { response } = await agent.chat({
+        message: 'Hello? Response to me "No"',
+      });
+      consola.debug("response:", response.message.content);
+      ok(extractText(response.message.content).includes("No"));
+    }
+    {
+      const { response } = await agent.chat({
+        message: 'Hello? Response to me "Maybe"',
+      });
+      consola.debug("response:", response.message.content);
+      ok(extractText(response.message.content).includes("Maybe"));
+    }
+    {
+      const { response } = await agent.chat({
+        message: "What is the weather in San Francisco?",
+      });
+      consola.debug("response:", response.message.content);
+      ok(extractText(response.message.content).includes("72"));
+    }
+    {
+      const { response } = await agent.chat({
+        message: "What is the weather in Shanghai?",
+      });
+      consola.debug("response:", response.message.content);
+      ok(extractText(response.message.content).includes("72"));
+    }
+  });
+});
@@ -0,0 +1,552 @@
+{
+  "llmEventStart": [
+    {
+      "id": "PRESERVE_0",
+      "messages": [
+        {
+          "role": "user",
+          "content": "Hello? Response to me \"Yes\""
+        }
+      ]
+    },
+    {
+      "id": "PRESERVE_1",
+      "messages": [
+        {
+          "role": "user",
+          "content": "Hello? Response to me \"Yes\""
+        },
+        {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Yes\".\n</thinking>\n\nYes"
+            }
+          ],
+          "role": "assistant",
+          "options": {}
+        },
+        {
+          "role": "user",
+          "content": "Hello? Response to me \"No\""
+        }
+      ]
+    },
+    {
+      "id": "PRESERVE_2",
+      "messages": [
+        {
+          "role": "user",
+          "content": "Hello? Response to me \"Yes\""
+        },
+        {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Yes\".\n</thinking>\n\nYes"
+            }
+          ],
+          "role": "assistant",
+          "options": {}
+        },
+        {
+          "role": "user",
+          "content": "Hello? Response to me \"No\""
+        },
+        {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"No\".\n</thinking>\n\nNo"
+            }
+          ],
+          "role": "assistant",
+          "options": {}
+        },
+        {
+          "role": "user",
+          "content": "Hello? Response to me \"Maybe\""
+        }
+      ]
+    },
+    {
+      "id": "PRESERVE_3",
+      "messages": [
+        {
+          "role": "user",
+          "content": "Hello? Response to me \"Yes\""
+        },
+        {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Yes\".\n</thinking>\n\nYes"
+            }
+          ],
+          "role": "assistant",
+          "options": {}
+        },
+        {
+          "role": "user",
+          "content": "Hello? Response to me \"No\""
+        },
+        {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"No\".\n</thinking>\n\nNo"
+            }
+          ],
+          "role": "assistant",
+          "options": {}
+        },
+        {
+          "role": "user",
+          "content": "Hello? Response to me \"Maybe\""
+        },
+        {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Maybe\".\n</thinking>\n\nMaybe"
+            }
+          ],
+          "role": "assistant",
+          "options": {}
+        },
+        {
+          "role": "user",
+          "content": "What is the weather in San Francisco?"
+        }
+      ]
+    },
+    {
+      "id": "PRESERVE_4",
+      "messages": [
+        {
+          "role": "user",
+          "content": "Hello? Response to me \"Yes\""
+        },
+        {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Yes\".\n</thinking>\n\nYes"
+            }
+          ],
+          "role": "assistant",
+          "options": {}
+        },
+        {
+          "role": "user",
+          "content": "Hello? Response to me \"No\""
+        },
+        {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"No\".\n</thinking>\n\nNo"
+            }
+          ],
+          "role": "assistant",
+          "options": {}
+        },
+        {
+          "role": "user",
+          "content": "Hello? Response to me \"Maybe\""
+        },
+        {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Maybe\".\n</thinking>\n\nMaybe"
+            }
+          ],
+          "role": "assistant",
+          "options": {}
+        },
+        {
+          "role": "user",
+          "content": "What is the weather in San Francisco?"
+        },
+        {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has asked for the weather in a specific city, San Francisco. The relevant tool to answer this is the getWeather function.\n\nLooking at the required parameters for getWeather:\ncity (string): The user directly provided the city \"San Francisco\"\n\nSince the required \"city\" parameter has been provided, we can proceed with the getWeather function call.\n</thinking>"
+            }
+          ],
+          "role": "assistant",
+          "options": {
+            "toolCall": {
+              "id": "toolu_01Gy7Gxbx7uGmjVncGH6pubL",
+              "name": "getWeather",
+              "input": {
+                "city": "San Francisco"
+              }
+            }
+          }
+        },
+        {
+          "content": "The weather in San Francisco is 72 degrees",
+          "role": "user",
+          "options": {
+            "toolResult": {
+              "result": "The weather in San Francisco is 72 degrees",
+              "isError": false,
+              "id": "toolu_01Gy7Gxbx7uGmjVncGH6pubL"
+            }
+          }
+        }
+      ]
+    },
+    {
+      "id": "PRESERVE_5",
+      "messages": [
+        {
+          "role": "user",
+          "content": "Hello? Response to me \"Yes\""
+        },
+        {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Yes\".\n</thinking>\n\nYes"
+            }
+          ],
+          "role": "assistant",
+          "options": {}
+        },
+        {
+          "role": "user",
+          "content": "Hello? Response to me \"No\""
+        },
+        {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"No\".\n</thinking>\n\nNo"
+            }
+          ],
+          "role": "assistant",
+          "options": {}
+        },
+        {
+          "role": "user",
+          "content": "Hello? Response to me \"Maybe\""
+        },
+        {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Maybe\".\n</thinking>\n\nMaybe"
+            }
+          ],
+          "role": "assistant",
+          "options": {}
+        },
+        {
+          "role": "user",
+          "content": "What is the weather in San Francisco?"
+        },
+        {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has asked for the weather in a specific city, San Francisco. The relevant tool to answer this is the getWeather function.\n\nLooking at the required parameters for getWeather:\ncity (string): The user directly provided the city \"San Francisco\"\n\nSince the required \"city\" parameter has been provided, we can proceed with the getWeather function call.\n</thinking>"
+            }
+          ],
+          "role": "assistant",
+          "options": {
+            "toolCall": {
+              "id": "toolu_01Gy7Gxbx7uGmjVncGH6pubL",
+              "name": "getWeather",
+              "input": {
+                "city": "San Francisco"
+              }
+            }
+          }
+        },
+        {
+          "content": "The weather in San Francisco is 72 degrees",
+          "role": "user",
+          "options": {
+            "toolResult": {
+              "result": "The weather in San Francisco is 72 degrees",
+              "isError": false,
+              "id": "toolu_01Gy7Gxbx7uGmjVncGH6pubL"
+            }
+          }
+        },
+        {
+          "content": [
+            {
+              "type": "text",
+              "text": "The current weather in San Francisco is 72 degrees."
+            }
+          ],
+          "role": "assistant",
+          "options": {}
+        },
+        {
+          "role": "user",
+          "content": "What is the weather in Shanghai?"
+        }
+      ]
+    },
+    {
+      "id": "PRESERVE_6",
+      "messages": [
+        {
+          "role": "user",
+          "content": "Hello? Response to me \"Yes\""
+        },
+        {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Yes\".\n</thinking>\n\nYes"
+            }
+          ],
+          "role": "assistant",
+          "options": {}
+        },
+        {
+          "role": "user",
+          "content": "Hello? Response to me \"No\""
+        },
+        {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"No\".\n</thinking>\n\nNo"
+            }
+          ],
+          "role": "assistant",
+          "options": {}
+        },
+        {
+          "role": "user",
+          "content": "Hello? Response to me \"Maybe\""
+        },
+        {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Maybe\".\n</thinking>\n\nMaybe"
+            }
+          ],
+          "role": "assistant",
+          "options": {}
+        },
+        {
+          "role": "user",
+          "content": "What is the weather in San Francisco?"
+        },
+        {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has asked for the weather in a specific city, San Francisco. The relevant tool to answer this is the getWeather function.\n\nLooking at the required parameters for getWeather:\ncity (string): The user directly provided the city \"San Francisco\"\n\nSince the required \"city\" parameter has been provided, we can proceed with the getWeather function call.\n</thinking>"
+            }
+          ],
+          "role": "assistant",
+          "options": {
+            "toolCall": {
+              "id": "toolu_01Gy7Gxbx7uGmjVncGH6pubL",
+              "name": "getWeather",
+              "input": {
+                "city": "San Francisco"
+              }
+            }
+          }
+        },
+        {
+          "content": "The weather in San Francisco is 72 degrees",
+          "role": "user",
+          "options": {
+            "toolResult": {
+              "result": "The weather in San Francisco is 72 degrees",
+              "isError": false,
+              "id": "toolu_01Gy7Gxbx7uGmjVncGH6pubL"
+            }
+          }
+        },
+        {
+          "content": [
+            {
+              "type": "text",
+              "text": "The current weather in San Francisco is 72 degrees."
+            }
+          ],
+          "role": "assistant",
+          "options": {}
+        },
+        {
+          "role": "user",
+          "content": "What is the weather in Shanghai?"
+        },
+        {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has asked for the weather in a specific city, Shanghai. The relevant tool to answer this is the getWeather function.\n\nLooking at the required parameters for getWeather:\ncity (string): The user directly provided the city \"Shanghai\"\n\nSince the required \"city\" parameter has been provided, we can proceed with the getWeather function call.\n</thinking>"
+            }
+          ],
+          "role": "assistant",
+          "options": {
+            "toolCall": {
+              "id": "toolu_01NHyahSUqrPjxQk9mvCvvGe",
+              "name": "getWeather",
+              "input": {
+                "city": "Shanghai"
+              }
+            }
+          }
+        },
+        {
+          "content": "The weather in Shanghai is 72 degrees",
+          "role": "user",
+          "options": {
+            "toolResult": {
+              "result": "The weather in Shanghai is 72 degrees",
+              "isError": false,
+              "id": "toolu_01NHyahSUqrPjxQk9mvCvvGe"
+            }
+          }
+        }
+      ]
+    }
+  ],
+  "llmEventEnd": [
+    {
+      "id": "PRESERVE_0",
+      "response": {
+        "raw": null,
+        "message": {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Yes\".\n</thinking>\n\nYes"
+            }
+          ],
+          "role": "assistant",
+          "options": {}
+        }
+      }
+    },
+    {
+      "id": "PRESERVE_1",
+      "response": {
+        "raw": null,
+        "message": {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"No\".\n</thinking>\n\nNo"
+            }
+          ],
+          "role": "assistant",
+          "options": {}
+        }
+      }
+    },
+    {
+      "id": "PRESERVE_2",
+      "response": {
+        "raw": null,
+        "message": {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Maybe\".\n</thinking>\n\nMaybe"
+            }
+          ],
+          "role": "assistant",
+          "options": {}
+        }
+      }
+    },
+    {
+      "id": "PRESERVE_3",
+      "response": {
+        "raw": null,
+        "message": {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has asked for the weather in a specific city, San Francisco. The relevant tool to answer this is the getWeather function.\n\nLooking at the required parameters for getWeather:\ncity (string): The user directly provided the city \"San Francisco\"\n\nSince the required \"city\" parameter has been provided, we can proceed with the getWeather function call.\n</thinking>"
+            }
+          ],
+          "role": "assistant",
+          "options": {
+            "toolCall": {
+              "id": "toolu_01Gy7Gxbx7uGmjVncGH6pubL",
+              "name": "getWeather",
+              "input": {
+                "city": "San Francisco"
+              }
+            }
+          }
+        }
+      }
+    },
+    {
+      "id": "PRESERVE_4",
+      "response": {
+        "raw": null,
+        "message": {
+          "content": [
+            {
+              "type": "text",
+              "text": "The current weather in San Francisco is 72 degrees."
+            }
+          ],
+          "role": "assistant",
+          "options": {}
+        }
+      }
+    },
+    {
+      "id": "PRESERVE_5",
+      "response": {
+        "raw": null,
+        "message": {
+          "content": [
+            {
+              "type": "text",
+              "text": "<thinking>\nThe user has asked for the weather in a specific city, Shanghai. The relevant tool to answer this is the getWeather function.\n\nLooking at the required parameters for getWeather:\ncity (string): The user directly provided the city \"Shanghai\"\n\nSince the required \"city\" parameter has been provided, we can proceed with the getWeather function call.\n</thinking>"
+            }
+          ],
+          "role": "assistant",
+          "options": {
+            "toolCall": {
+              "id": "toolu_01NHyahSUqrPjxQk9mvCvvGe",
+              "name": "getWeather",
+              "input": {
+                "city": "Shanghai"
+              }
+            }
+          }
+        }
+      }
+    },
+    {
+      "id": "PRESERVE_6",
+      "response": {
+        "raw": null,
+        "message": {
+          "content": [
+            {
+              "type": "text",
+              "text": "The current weather in Shanghai is 72 degrees."
+            }
+          ],
+          "role": "assistant",
+          "options": {}
+        }
+      }
+    }
+  ],
+  "llmEventStream": []
+}
@@ -1,7 +1,7 @@
 {
  "name": "@llamaindex/core-e2e",
  "private": true,
-  "version": "0.0.3",
+  "version": "0.0.4",
  "type": "module",
  "scripts": {
    "e2e": "node --import tsx --import ./mock-register.js --test ./node/*.e2e.ts",
@@ -1,8 +1,11 @@
 {
  "name": "@llamaindex/core",
-  "version": "0.3.4",
+  "version": "0.3.6",
  "exports": "./src/index.ts",
  "imports": {
-    "@llamaindex/env": "jsr:@llamaindex/env@0.0.6"
+    "@llamaindex/env": "jsr:@llamaindex/env@0.1.2"
+  },
+  "publish": {
+    "include": ["LICENSE", "README.md", "src/**/*", "jsr.json"]
  }
 }
@@ -1,9 +1,25 @@
 {
  "name": "llamaindex",
-  "version": "0.3.4",
+  "version": "0.3.6",
  "expectedMinorVersion": "3",
  "license": "MIT",
  "type": "module",
+  "keywords": [
+    "llm",
+    "llama",
+    "openai",
+    "gpt",
+    "data science",
+    "prompt",
+    "prompt engineering",
+    "chatgpt",
+    "machine learning",
+    "ml",
+    "embedding",
+    "vectorstore",
+    "data framework",
+    "llamaindex"
+  ],
  "dependencies": {
    "@anthropic-ai/sdk": "^0.20.6",
    "@aws-crypto/sha256-js": "^5.2.0",
@@ -32,7 +48,6 @@
    "md-utils-ts": "^2.0.0",
    "mongodb": "^6.5.0",
    "notion-md-crawler": "^1.0.0",
-    "ollama": "^0.5.0",
    "openai": "^4.38.0",
    "papaparse": "^5.4.1",
    "pathe": "^1.1.2",
@@ -348,6 +348,8 @@ export abstract class AgentRunner<
        >,
      ) => {
        for await (const stepOutput of iter) {
+          // update chat history for each round
+          this.#chatHistory = [...stepOutput.taskStep.context.store.messages];
          if (stepOutput.isLast) {
            return stepOutput;
          }
@@ -356,7 +358,6 @@ export abstract class AgentRunner<
      },
    );
    const { output, taskStep } = stepOutput;
-    this.#chatHistory = [...taskStep.context.store.messages];
    if (isAsyncIterable(output)) {
      return output.pipeThrough<
        AgentStreamChatResponse<AdditionalMessageOptions>
@@ -0,0 +1,264 @@
+type Fetch = typeof fetch;
+interface Config {
+  host: string;
+  fetch?: Fetch;
+  proxy?: boolean;
+}
+interface Options {
+  numa: boolean;
+  num_ctx: number;
+  num_batch: number;
+  main_gpu: number;
+  low_vram: boolean;
+  f16_kv: boolean;
+  logits_all: boolean;
+  vocab_only: boolean;
+  use_mmap: boolean;
+  use_mlock: boolean;
+  embedding_only: boolean;
+  num_thread: number;
+  num_keep: number;
+  seed: number;
+  num_predict: number;
+  top_k: number;
+  top_p: number;
+  tfs_z: number;
+  typical_p: number;
+  repeat_last_n: number;
+  temperature: number;
+  repeat_penalty: number;
+  presence_penalty: number;
+  frequency_penalty: number;
+  mirostat: number;
+  mirostat_tau: number;
+  mirostat_eta: number;
+  penalize_newline: boolean;
+  stop: string[];
+}
+interface GenerateRequest {
+  model: string;
+  prompt: string;
+  system?: string;
+  template?: string;
+  context?: number[];
+  stream?: boolean;
+  raw?: boolean;
+  format?: string;
+  images?: Uint8Array[] | string[];
+  keep_alive?: string | number;
+  options?: Partial<Options>;
+}
+interface Message {
+  role: string;
+  content: string;
+  images?: Uint8Array[] | string[];
+}
+interface ChatRequest {
+  model: string;
+  messages?: Message[];
+  stream?: boolean;
+  format?: string;
+  keep_alive?: string | number;
+  options?: Partial<Options>;
+}
+interface PullRequest {
+  model: string;
+  insecure?: boolean;
+  stream?: boolean;
+}
+interface PushRequest {
+  model: string;
+  insecure?: boolean;
+  stream?: boolean;
+}
+interface CreateRequest {
+  model: string;
+  path?: string;
+  modelfile?: string;
+  stream?: boolean;
+}
+interface DeleteRequest {
+  model: string;
+}
+interface CopyRequest {
+  source: string;
+  destination: string;
+}
+interface ShowRequest {
+  model: string;
+  system?: string;
+  template?: string;
+  options?: Partial<Options>;
+}
+interface EmbeddingsRequest {
+  model: string;
+  prompt: string;
+  keep_alive?: string | number;
+  options?: Partial<Options>;
+}
+interface GenerateResponse {
+  model: string;
+  created_at: Date;
+  response: string;
+  done: boolean;
+  context: number[];
+  total_duration: number;
+  load_duration: number;
+  prompt_eval_count: number;
+  prompt_eval_duration: number;
+  eval_count: number;
+  eval_duration: number;
+}
+interface ChatResponse {
+  model: string;
+  created_at: Date;
+  message: Message;
+  done: boolean;
+  total_duration: number;
+  load_duration: number;
+  prompt_eval_count: number;
+  prompt_eval_duration: number;
+  eval_count: number;
+  eval_duration: number;
+}
+interface EmbeddingsResponse {
+  embedding: number[];
+}
+interface ProgressResponse {
+  status: string;
+  digest: string;
+  total: number;
+  completed: number;
+}
+interface ModelResponse {
+  name: string;
+  modified_at: Date;
+  size: number;
+  digest: string;
+  details: ModelDetails;
+}
+interface ModelDetails {
+  parent_model: string;
+  format: string;
+  family: string;
+  families: string[];
+  parameter_size: string;
+  quantization_level: string;
+}
+interface ShowResponse {
+  license: string;
+  modelfile: string;
+  parameters: string;
+  template: string;
+  system: string;
+  details: ModelDetails;
+  messages: Message[];
+}
+interface ListResponse {
+  models: ModelResponse[];
+}
+interface ErrorResponse {
+  error: string;
+}
+interface StatusResponse {
+  status: string;
+}
+
+declare class Ollama {
+  protected readonly config: Config;
+  protected readonly fetch: Fetch;
+  private abortController;
+  constructor(config?: Partial<Config>);
+  abort(): void;
+  protected processStreamableRequest<T extends object>(
+    endpoint: string,
+    request: {
+      stream?: boolean;
+    } & Record<string, any>,
+  ): Promise<T | AsyncGenerator<T>>;
+  encodeImage(image: Uint8Array | string): Promise<string>;
+  generate(
+    request: GenerateRequest & {
+      stream: true;
+    },
+  ): Promise<AsyncGenerator<GenerateResponse>>;
+  generate(
+    request: GenerateRequest & {
+      stream?: false;
+    },
+  ): Promise<GenerateResponse>;
+  chat(
+    request: ChatRequest & {
+      stream: true;
+    },
+  ): Promise<AsyncGenerator<ChatResponse>>;
+  chat(
+    request: ChatRequest & {
+      stream?: false;
+    },
+  ): Promise<ChatResponse>;
+  create(
+    request: CreateRequest & {
+      stream: true;
+    },
+  ): Promise<AsyncGenerator<ProgressResponse>>;
+  create(
+    request: CreateRequest & {
+      stream?: false;
+    },
+  ): Promise<ProgressResponse>;
+  pull(
+    request: PullRequest & {
+      stream: true;
+    },
+  ): Promise<AsyncGenerator<ProgressResponse>>;
+  pull(
+    request: PullRequest & {
+      stream?: false;
+    },
+  ): Promise<ProgressResponse>;
+  push(
+    request: PushRequest & {
+      stream: true;
+    },
+  ): Promise<AsyncGenerator<ProgressResponse>>;
+  push(
+    request: PushRequest & {
+      stream?: false;
+    },
+  ): Promise<ProgressResponse>;
+  delete(request: DeleteRequest): Promise<StatusResponse>;
+  copy(request: CopyRequest): Promise<StatusResponse>;
+  list(): Promise<ListResponse>;
+  show(request: ShowRequest): Promise<ShowResponse>;
+  embeddings(request: EmbeddingsRequest): Promise<EmbeddingsResponse>;
+}
+declare const _default: Ollama;
+
+export {
+  Ollama,
+  _default as default,
+  type ChatRequest,
+  type ChatResponse,
+  type Config,
+  type CopyRequest,
+  type CreateRequest,
+  type DeleteRequest,
+  type EmbeddingsRequest,
+  type EmbeddingsResponse,
+  type ErrorResponse,
+  type Fetch,
+  type GenerateRequest,
+  type GenerateResponse,
+  type ListResponse,
+  type Message,
+  type ModelDetails,
+  type ModelResponse,
+  type Options,
+  type ProgressResponse,
+  type PullRequest,
+  type PushRequest,
+  type ShowRequest,
+  type ShowResponse,
+  type StatusResponse,
+};
@@ -0,0 +1,462 @@
+// generate from "tsup ./src/browser.js --format esm --dts"
+var __defProp = Object.defineProperty;
+var __getOwnPropSymbols = Object.getOwnPropertySymbols;
+var __hasOwnProp = Object.prototype.hasOwnProperty;
+var __propIsEnum = Object.prototype.propertyIsEnumerable;
+var __knownSymbol = (name, symbol) => {
+  return (symbol = Symbol[name]) ? symbol : Symbol.for("Symbol." + name);
+};
+var __defNormalProp = (obj, key, value) =>
+  key in obj
+    ? __defProp(obj, key, {
+        enumerable: true,
+        configurable: true,
+        writable: true,
+        value,
+      })
+    : (obj[key] = value);
+var __spreadValues = (a, b) => {
+  for (var prop in b || (b = {}))
+    if (__hasOwnProp.call(b, prop)) __defNormalProp(a, prop, b[prop]);
+  if (__getOwnPropSymbols)
+    for (var prop of __getOwnPropSymbols(b)) {
+      if (__propIsEnum.call(b, prop)) __defNormalProp(a, prop, b[prop]);
+    }
+  return a;
+};
+var __async = (__this, __arguments, generator) => {
+  return new Promise((resolve, reject) => {
+    var fulfilled = (value) => {
+      try {
+        step(generator.next(value));
+      } catch (e) {
+        reject(e);
+      }
+    };
+    var rejected = (value) => {
+      try {
+        step(generator.throw(value));
+      } catch (e) {
+        reject(e);
+      }
+    };
+    var step = (x) =>
+      x.done
+        ? resolve(x.value)
+        : Promise.resolve(x.value).then(fulfilled, rejected);
+    step((generator = generator.apply(__this, __arguments)).next());
+  });
+};
+var __await = function (promise, isYieldStar) {
+  this[0] = promise;
+  this[1] = isYieldStar;
+};
+var __asyncGenerator = (__this, __arguments, generator) => {
+  var resume = (k, v, yes, no) => {
+    try {
+      var x = generator[k](v),
+        isAwait = (v = x.value) instanceof __await,
+        done = x.done;
+      Promise.resolve(isAwait ? v[0] : v)
+        .then((y) =>
+          isAwait
+            ? resume(
+                k === "return" ? k : "next",
+                v[1] ? { done: y.done, value: y.value } : y,
+                yes,
+                no,
+              )
+            : yes({ value: y, done }),
+        )
+        .catch((e) => resume("throw", e, yes, no));
+    } catch (e) {
+      no(e);
+    }
+  };
+  var method = (k) =>
+    (it[k] = (x) => new Promise((yes, no) => resume(k, x, yes, no)));
+  var it = {};
+  return (
+    (generator = generator.apply(__this, __arguments)),
+    (it[__knownSymbol("asyncIterator")] = () => it),
+    method("next"),
+    method("throw"),
+    method("return"),
+    it
+  );
+};
+var __forAwait = (obj, it, method) =>
+  (it = obj[__knownSymbol("asyncIterator")])
+    ? it.call(obj)
+    : ((obj = obj[__knownSymbol("iterator")]()),
+      (it = {}),
+      (method = (key, fn) =>
+        (fn = obj[key]) &&
+        (it[key] = (arg) =>
+          new Promise(
+            (yes, no, done) => (
+              (arg = fn.call(obj, arg)),
+              (done = arg.done),
+              Promise.resolve(arg.value).then(
+                (value) => yes({ value, done }),
+                no,
+              )
+            ),
+          ))),
+      method("next"),
+      method("return"),
+      it);
+
+// src/version.ts
+var version = "0.0.0";
+
+// src/utils.ts
+var ResponseError = class _ResponseError extends Error {
+  constructor(error, status_code) {
+    super(error);
+    this.error = error;
+    this.status_code = status_code;
+    this.name = "ResponseError";
+    if (Error.captureStackTrace) {
+      Error.captureStackTrace(this, _ResponseError);
+    }
+  }
+};
+var checkOk = (response) =>
+  __async(void 0, null, function* () {
+    var _a;
+    if (!response.ok) {
+      let message = `Error ${response.status}: ${response.statusText}`;
+      let errorData = null;
+      if (
+        (_a = response.headers.get("content-type")) == null
+          ? void 0
+          : _a.includes("application/json")
+      ) {
+        try {
+          errorData = yield response.json();
+          message = errorData.error || message;
+        } catch (error) {
+          console.log("Failed to parse error response as JSON");
+        }
+      } else {
+        try {
+          console.log("Getting text from response");
+          const textResponse = yield response.text();
+          message = textResponse || message;
+        } catch (error) {
+          console.log("Failed to get text from error response");
+        }
+      }
+      throw new ResponseError(message, response.status);
+    }
+  });
+function getPlatform() {
+  if (typeof window !== "undefined" && window.navigator) {
+    return `${window.navigator.platform.toLowerCase()} Browser/${navigator.userAgent};`;
+  } else if (typeof process !== "undefined") {
+    return `${process.arch} ${process.platform} Node.js/${process.version}`;
+  }
+  return "";
+}
+var fetchWithHeaders = (_0, _1, ..._2) =>
+  __async(void 0, [_0, _1, ..._2], function* (fetch2, url, options = {}) {
+    const defaultHeaders = {
+      "Content-Type": "application/json",
+      Accept: "application/json",
+      "User-Agent": `ollama-js/${version} (${getPlatform()})`,
+    };
+    if (!options.headers) {
+      options.headers = {};
+    }
+    options.headers = __spreadValues(
+      __spreadValues({}, defaultHeaders),
+      options.headers,
+    );
+    return fetch2(url, options);
+  });
+var get = (fetch2, host) =>
+  __async(void 0, null, function* () {
+    const response = yield fetchWithHeaders(fetch2, host);
+    yield checkOk(response);
+    return response;
+  });
+var post = (fetch2, host, data, options) =>
+  __async(void 0, null, function* () {
+    const isRecord = (input) => {
+      return (
+        input !== null && typeof input === "object" && !Array.isArray(input)
+      );
+    };
+    const formattedData = isRecord(data) ? JSON.stringify(data) : data;
+    const response = yield fetchWithHeaders(fetch2, host, {
+      method: "POST",
+      body: formattedData,
+      signal: options == null ? void 0 : options.signal,
+    });
+    yield checkOk(response);
+    return response;
+  });
+var del = (fetch2, host, data) =>
+  __async(void 0, null, function* () {
+    const response = yield fetchWithHeaders(fetch2, host, {
+      method: "DELETE",
+      body: JSON.stringify(data),
+    });
+    yield checkOk(response);
+    return response;
+  });
+var parseJSON = function (itr) {
+  return __asyncGenerator(this, null, function* () {
+    var _a;
+    const decoder = new TextDecoder("utf-8");
+    let buffer = "";
+    const reader = itr.getReader();
+    while (true) {
+      const { done, value: chunk } = yield new __await(reader.read());
+      if (done) {
+        break;
+      }
+      buffer += decoder.decode(chunk);
+      const parts = buffer.split("\n");
+      buffer = (_a = parts.pop()) != null ? _a : "";
+      for (const part of parts) {
+        try {
+          yield JSON.parse(part);
+        } catch (error) {
+          console.warn("invalid json: ", part);
+        }
+      }
+    }
+    for (const part of buffer.split("\n").filter((p) => p !== "")) {
+      try {
+        yield JSON.parse(part);
+      } catch (error) {
+        console.warn("invalid json: ", part);
+      }
+    }
+  });
+};
+var formatHost = (host) => {
+  if (!host) {
+    return "http://127.0.0.1:11434";
+  }
+  let isExplicitProtocol = host.includes("://");
+  if (host.startsWith(":")) {
+    host = `http://127.0.0.1${host}`;
+    isExplicitProtocol = false;
+  }
+  if (!isExplicitProtocol) {
+    host = `http://${host}`;
+  }
+  const url = new URL(host);
+  let port = url.port;
+  if (!port) {
+    if (!isExplicitProtocol) {
+      port = "11434";
+    } else {
+      port = url.protocol === "https:" ? "443" : "80";
+    }
+  }
+  let formattedHost = `${url.protocol}//${url.hostname}:${port}${url.pathname}`;
+  if (formattedHost.endsWith("/")) {
+    formattedHost = formattedHost.slice(0, -1);
+  }
+  return formattedHost;
+};
+
+// src/browser.ts
+// import "whatwg-fetch";
+var Ollama = class {
+  constructor(config) {
+    var _a;
+    this.config = {
+      host: "",
+    };
+    if (!(config == null ? void 0 : config.proxy)) {
+      this.config.host = formatHost(
+        (_a = config == null ? void 0 : config.host) != null
+          ? _a
+          : "http://127.0.0.1:11434",
+      );
+    }
+    this.fetch = fetch;
+    if ((config == null ? void 0 : config.fetch) != null) {
+      this.fetch = config.fetch;
+    }
+    this.abortController = new AbortController();
+  }
+  // Abort any ongoing requests to Ollama
+  abort() {
+    this.abortController.abort();
+    this.abortController = new AbortController();
+  }
+  processStreamableRequest(endpoint, request) {
+    return __async(this, null, function* () {
+      var _a;
+      request.stream = (_a = request.stream) != null ? _a : false;
+      const response = yield post(
+        this.fetch,
+        `${this.config.host}/api/${endpoint}`,
+        __spreadValues({}, request),
+        { signal: this.abortController.signal },
+      );
+      if (!response.body) {
+        throw new Error("Missing body");
+      }
+      const itr = parseJSON(response.body);
+      if (request.stream) {
+        return (function () {
+          return __asyncGenerator(this, null, function* () {
+            try {
+              for (
+                var iter = __forAwait(itr), more, temp, error;
+                (more = !(temp = yield new __await(iter.next())).done);
+                more = false
+              ) {
+                const message = temp.value;
+                if ("error" in message) {
+                  throw new Error(message.error);
+                }
+                yield message;
+                if (message.done || message.status === "success") {
+                  return;
+                }
+              }
+            } catch (temp) {
+              error = [temp];
+            } finally {
+              try {
+                more &&
+                  (temp = iter.return) &&
+                  (yield new __await(temp.call(iter)));
+              } finally {
+                if (error) throw error[0];
+              }
+            }
+            throw new Error(
+              "Did not receive done or success response in stream.",
+            );
+          });
+        })();
+      } else {
+        const message = yield itr.next();
+        if (!message.value.done && message.value.status !== "success") {
+          throw new Error("Expected a completed response.");
+        }
+        return message.value;
+      }
+    });
+  }
+  encodeImage(image) {
+    return __async(this, null, function* () {
+      if (typeof image !== "string") {
+        const uint8Array = new Uint8Array(image);
+        const numberArray = Array.from(uint8Array);
+        const base64String = btoa(String.fromCharCode.apply(null, numberArray));
+        return base64String;
+      }
+      return image;
+    });
+  }
+  generate(request) {
+    return __async(this, null, function* () {
+      if (request.images) {
+        request.images = yield Promise.all(
+          request.images.map(this.encodeImage.bind(this)),
+        );
+      }
+      return this.processStreamableRequest("generate", request);
+    });
+  }
+  chat(request) {
+    return __async(this, null, function* () {
+      if (request.messages) {
+        for (const message of request.messages) {
+          if (message.images) {
+            message.images = yield Promise.all(
+              message.images.map(this.encodeImage.bind(this)),
+            );
+          }
+        }
+      }
+      return this.processStreamableRequest("chat", request);
+    });
+  }
+  create(request) {
+    return __async(this, null, function* () {
+      return this.processStreamableRequest("create", {
+        name: request.model,
+        stream: request.stream,
+        modelfile: request.modelfile,
+      });
+    });
+  }
+  pull(request) {
+    return __async(this, null, function* () {
+      return this.processStreamableRequest("pull", {
+        name: request.model,
+        stream: request.stream,
+        insecure: request.insecure,
+      });
+    });
+  }
+  push(request) {
+    return __async(this, null, function* () {
+      return this.processStreamableRequest("push", {
+        name: request.model,
+        stream: request.stream,
+        insecure: request.insecure,
+      });
+    });
+  }
+  delete(request) {
+    return __async(this, null, function* () {
+      yield del(this.fetch, `${this.config.host}/api/delete`, {
+        name: request.model,
+      });
+      return { status: "success" };
+    });
+  }
+  copy(request) {
+    return __async(this, null, function* () {
+      yield post(
+        this.fetch,
+        `${this.config.host}/api/copy`,
+        __spreadValues({}, request),
+      );
+      return { status: "success" };
+    });
+  }
+  list() {
+    return __async(this, null, function* () {
+      const response = yield get(this.fetch, `${this.config.host}/api/tags`);
+      const listResponse = yield response.json();
+      return listResponse;
+    });
+  }
+  show(request) {
+    return __async(this, null, function* () {
+      const response = yield post(
+        this.fetch,
+        `${this.config.host}/api/show`,
+        __spreadValues({}, request),
+      );
+      const showResponse = yield response.json();
+      return showResponse;
+    });
+  }
+  embeddings(request) {
+    return __async(this, null, function* () {
+      const response = yield post(
+        this.fetch,
+        `${this.config.host}/api/embeddings`,
+        __spreadValues({}, request),
+      );
+      const embeddingsResponse = yield response.json();
+      return embeddingsResponse;
+    });
+  }
+};
+var browser_default = new Ollama();
+export { Ollama, browser_default as default };
@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 Saul
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
@@ -156,58 +156,104 @@ export class Anthropic extends ToolCallLLM<AnthropicAdditionalChatOptions> {
  formatMessages<Beta = false>(
    messages: ChatMessage<ToolCallLLMMessageOptions>[],
  ): Beta extends true ? ToolsBetaMessageParam[] : MessageParam[] {
-    return messages.map<any>((message) => {
-      if (message.role !== "user" && message.role !== "assistant") {
-        throw new Error("Unsupported Anthropic role");
-      }
-      const options = message.options ?? {};
-      if ("toolResult" in options) {
-        const { id, isError } = options.toolResult;
-        return {
-          role: "user",
-          content: [
-            {
-              type: "tool_result",
-              is_error: isError,
-              content: [
-                {
-                  type: "text",
-                  text: extractText(message.content),
-                },
-              ],
-              tool_use_id: id,
-            },
-          ] satisfies ToolResultBlockParam[],
-        } satisfies ToolsBetaMessageParam;
-      } else if ("toolCall" in options) {
-        const aiThinkingText = extractText(message.content);
-        return {
-          role: "assistant",
-          content: [
-            // this could be empty when you call two tools in one query
-            ...(aiThinkingText.trim()
-              ? [
+    const result: ToolsBetaMessageParam[] = messages
+      .filter(
+        (message) => message.role === "user" || message.role === "assistant",
+      )
+      .map((message) => {
+        const options = message.options ?? {};
+        if ("toolResult" in options) {
+          const { id, isError } = options.toolResult;
+          return {
+            role: "user",
+            content: [
+              {
+                type: "tool_result",
+                is_error: isError,
+                content: [
                  {
                    type: "text",
-                    text: aiThinkingText,
-                  } satisfies TextBlockParam,
-                ]
-              : []),
-            {
-              type: "tool_use",
-              id: options.toolCall.id,
-              name: options.toolCall.name,
-              input: options.toolCall.input,
-            } satisfies ToolUseBlockParam,
-          ] satisfies ToolsBetaContentBlock[],
-        } satisfies ToolsBetaMessageParam;
-      }
+                    text: extractText(message.content),
+                  },
+                ],
+                tool_use_id: id,
+              },
+            ] satisfies ToolResultBlockParam[],
+          } satisfies ToolsBetaMessageParam;
+        } else if ("toolCall" in options) {
+          const aiThinkingText = extractText(message.content);
+          return {
+            role: "assistant",
+            content: [
+              // this could be empty when you call two tools in one query
+              ...(aiThinkingText.trim()
+                ? [
+                    {
+                      type: "text",
+                      text: aiThinkingText,
+                    } satisfies TextBlockParam,
+                  ]
+                : []),
+              {
+                type: "tool_use",
+                id: options.toolCall.id,
+                name: options.toolCall.name,
+                input: options.toolCall.input,
+              } satisfies ToolUseBlockParam,
+            ] satisfies ToolsBetaContentBlock[],
+          } satisfies ToolsBetaMessageParam;
+        }

-      return {
-        content: extractText(message.content),
-        role: message.role,
-      } satisfies MessageParam;
-    });
+        return {
+          content: extractText(message.content),
+          role: message.role as "user" | "assistant",
+        } satisfies MessageParam;
+      });
+    // merge messages with the same role
+    // in case of 'messages: roles must alternate between "user" and "assistant", but found multiple "user" roles in a row'
+    const realResult: ToolsBetaMessageParam[] = [];
+    for (let i = 0; i < result.length; i++) {
+      if (i === 0) {
+        realResult.push(result[i]);
+        continue;
+      }
+      const current = result[i];
+      const previous = result[i - 1];
+      if (current.role === previous.role) {
+        // merge two messages with the same role
+        if (Array.isArray(previous.content)) {
+          if (Array.isArray(current.content)) {
+            previous.content.push(...current.content);
+          } else {
+            previous.content.push({
+              type: "text",
+              text: current.content,
+            });
+          }
+        } else {
+          if (Array.isArray(current.content)) {
+            previous.content = [
+              {
+                type: "text",
+                text: previous.content,
+              },
+              ...current.content,
+            ];
+          } else {
+            previous.content += `\n${current.content}`;
+          }
+        }
+        // no need to push the message
+      }
+      // if the roles are different, just push the message
+      else {
+        realResult.push(current);
+      }
+    }
+
+    return realResult as Beta extends true
+      ? ToolsBetaMessageParam[]
+      : MessageParam[];
  }

  chat(
@@ -1,3 +1,4 @@
+import { BaseEmbedding } from "../embeddings/types.js";
 import ollama, {
  type CreateRequest,
  type ChatResponse as OllamaChatResponse,
@@ -5,8 +6,7 @@ import ollama, {
  type Options,
  type ProgressResponse,
  type ShowRequest,
-} from "ollama/browser";
-import { BaseEmbedding } from "../embeddings/types.js";
+} from "../internal/deps/ollama.js";
 import type {
  ChatResponse,
  ChatResponseChunk,
@@ -106,12 +106,32 @@ export class ChromaVectorStore implements VectorStore {
      throw new Error("ChromaDB does not support querying by mode");
    }

-    const chromaWhere: { [x: string]: string | number | boolean } = {};
+    // fixme: type is broken
+    let chromaWhere: any = {};
    if (query.filters?.filters) {
      query.filters.filters.map((filter) => {
        const filterKey = filter.key;
        const filterValue = filter.value;
-        chromaWhere[filterKey] = filterValue;
+        if (filterKey in chromaWhere || "$or" in chromaWhere) {
+          if (!chromaWhere["$or"]) {
+            chromaWhere = {
+              $or: [
+                {
+                  ...chromaWhere,
+                },
+                {
+                  [filterKey]: filterValue,
+                },
+              ],
+            };
+          } else {
+            chromaWhere["$or"].push({
+              [filterKey]: filterValue,
+            });
+          }
+        } else {
+          chromaWhere[filterKey] = filterValue;
+        }
      });
    }

@@ -130,6 +150,7 @@ export class ChromaVectorStore implements VectorStore {
        IncludeEnum.Embeddings,
      ],
    });
+
    const vectorStoreQueryResult: VectorStoreQueryResult = {
      nodes: queryResponse.ids[0].map((id, index) => {
        const text = (queryResponse.documents as string[][])[0][index];
@@ -250,7 +250,7 @@ export class PGVectorStore implements VectorStore {
    options?: any,
  ): Promise<VectorStoreQueryResult> {
    // TODO QUERY TYPES:
-    //    Distance:       SELECT embedding <-> $1 AS distance FROM items;
+    //    Distance:       SELECT embedding <=> $1 AS distance FROM items;
    //    Inner Product:  SELECT (embedding <#> $1) * -1 AS inner_product FROM items;
    //    Cosine Sim:     SELECT 1 - (embedding <=> $1) AS cosine_similarity FROM items;

@@ -273,7 +273,7 @@ export class PGVectorStore implements VectorStore {

    const sql = `SELECT 
        v.*, 
-        embeddings <-> $1 s 
+        embeddings <=> $1 s 
      FROM ${this.schemaName}.${this.tableName} v
      ${where}
      ORDER BY s 
@@ -1,5 +1,11 @@
 # @llamaindex/core-test

+## 0.0.3
+
+### Patch Changes
+
+- be5df5b: fix: anthropic agent on multiple chat
+
 ## 0.0.2

 ### Patch Changes
@@ -0,0 +1,66 @@
+import { setEnvs } from "@llamaindex/env";
+import { Anthropic } from "llamaindex";
+import { beforeAll, describe, expect, test } from "vitest";
+
+beforeAll(() => {
+  setEnvs({
+    ANTHROPIC_API_KEY: "valid",
+  });
+});
+
+describe("Anthropic llm", () => {
+  test("format messages", () => {
+    const anthropic = new Anthropic();
+    expect(
+      anthropic.formatMessages([
+        {
+          content: "You are a helpful assistant.",
+          role: "assistant",
+        },
+        {
+          content: "Hello?",
+          role: "user",
+        },
+      ]),
+    ).toEqual([
+      {
+        content: "You are a helpful assistant.",
+        role: "assistant",
+      },
+      {
+        content: "Hello?",
+        role: "user",
+      },
+    ]);
+
+    expect(
+      anthropic.formatMessages([
+        {
+          content: "You are a helpful assistant.",
+          role: "assistant",
+        },
+        {
+          content: "Hello?",
+          role: "user",
+        },
+        {
+          content: "I am a system message.",
+          role: "system",
+        },
+        {
+          content: "What is your name?",
+          role: "user",
+        },
+      ]),
+    ).toEqual([
+      {
+        content: "You are a helpful assistant.",
+        role: "assistant",
+      },
+      {
+        content: "Hello?\nWhat is your name?",
+        role: "user",
+      },
+    ]);
+  });
+});
@@ -1,7 +1,7 @@
 {
  "name": "@llamaindex/core-test",
  "private": true,
-  "version": "0.0.2",
+  "version": "0.0.3",
  "type": "module",
  "scripts": {
    "test": "vitest run"
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/edge",
-  "version": "0.3.4",
+  "version": "0.3.6",
  "license": "MIT",
  "type": "module",
  "dependencies": {
@@ -31,7 +31,6 @@
    "md-utils-ts": "^2.0.0",
    "mongodb": "^6.5.0",
    "notion-md-crawler": "^1.0.0",
-    "ollama": "^0.5.0",
    "openai": "^4.38.0",
    "papaparse": "^5.4.1",
    "pathe": "^1.1.2",
@@ -1,5 +1,18 @@
 # @llamaindex/env

+## 0.1.2
+
+### Patch Changes
+
+- efa326a: chore: update package.json
+- efa326a: refactor: remove usage of lodash
+
+## 0.1.1
+
+### Patch Changes
+
+- 5596e31: feat: improve `@llamaindex/env`
+
 ## 0.1.0

 ### Minor Changes
@@ -0,0 +1,7 @@
+# @llamaindex/env
+
+> Environment wrapper, supports all JS environment including node, deno, bun, edge runtime, and cloudflare worker.
+
+## LICENSE
+
+MIT
@@ -1,8 +1,11 @@
 {
  "name": "@llamaindex/env",
-  "version": "0.1.0",
+  "version": "0.1.2",
  "exports": {
    ".": "./src/index.ts",
    "./type": "./src/type.ts"
+  },
+  "publish": {
+    "include": ["LICENSE", "README.md", "src/**/*.ts", "jsr.json"]
  }
 }
@@ -1,10 +1,26 @@
 {
  "name": "@llamaindex/env",
-  "description": "environment wrapper",
-  "version": "0.1.0",
+  "description": "environment wrapper, supports all JS environment including node, deno, bun, edge runtime, and cloudflare worker",
+  "version": "0.1.2",
  "type": "module",
  "types": "dist/type/index.d.ts",
  "main": "dist/cjs/index.js",
+  "keywords": [
+    "llm",
+    "llama",
+    "openai",
+    "gpt",
+    "data science",
+    "prompt",
+    "prompt engineering",
+    "chatgpt",
+    "machine learning",
+    "ml",
+    "embedding",
+    "vectorstore",
+    "data framework",
+    "llamaindex"
+  ],
  "exports": {
    ".": {
      "node": {
@@ -67,12 +83,22 @@
  },
  "dependencies": {
    "@types/lodash": "^4.14.202",
-    "@types/node": "^20.12.7",
-    "lodash": "^4.17.21"
+    "@types/node": "^20.12.7"
  },
  "peerDependencies": {
    "@aws-crypto/sha256-js": "^5.2.0",
    "pathe": "^1.1.2",
    "readable-stream": "^4.5.2"
+  },
+  "peerDependenciesMeta": {
+    "@aws-crypto/sha256-js": {
+      "optional": true
+    },
+    "pathe": {
+      "optional": true
+    },
+    "readable-stream": {
+      "optional": true
+    }
  }
 }
@@ -1,3 +1,10 @@
+/**
+ * Polyfill implementation some node.js APIs.
+ *
+ * The code should be compatible with any JS runtime.
+ *
+ * @module
+ */
 import { Sha256 } from "@aws-crypto/sha256-js";
 import pathe from "pathe";
 import { InMemoryFileSystem, type CompleteFileSystem } from "./type.js";
@@ -1,3 +1,16 @@
+/**
+ * This module is under Node.js environment.
+ * It provides a set of APIs to interact with the file system, streams, and other Node.js built-in modules.
+ *
+ * Use this under "node" condition,
+ *
+ * For example:
+ * ```shell
+ * node -e "const env = require('@llamaindex/env');"
+ * ```
+ *
+ * @module
+ */
 import { ok } from "node:assert";
 import { createHash, randomUUID } from "node:crypto";
 import fs from "node:fs/promises";
@@ -1,3 +1,10 @@
+/**
+ * This module is under Cloudflare Workers environment.
+ *
+ * Most of Node.js APIs are not available in Cloudflare Workers environment.
+ *
+ * @module
+ */
 import { INTERNAL_ENV } from "./utils.js";

 export * from "./index.polyfill.js";
@@ -1,5 +1,3 @@
-import _ from "lodash";
-
 /**
 * A filesystem interface that is meant to be compatible with
 * the 'fs' module from Node.js.
@@ -41,14 +39,14 @@ export class InMemoryFileSystem implements CompleteFileSystem {
    content: string,
    options?: unknown,
  ): Promise<void> {
-    this.files[path] = _.cloneDeep(content);
+    this.files[path] = structuredClone(content);
  }

  async readFile(path: string): Promise<string> {
    if (!(path in this.files)) {
      throw new Error(`File ${path} does not exist`);
    }
-    return _.cloneDeep(this.files[path]);
+    return structuredClone(this.files[path]);
  }

  async access(path: string): Promise<void> {
@@ -58,7 +56,7 @@ export class InMemoryFileSystem implements CompleteFileSystem {
  }

  async mkdir(path: string): Promise<undefined> {
-    this.files[path] = _.get(this.files, path, null);
+    this.files[path] = this.files[path] ?? null;
  }

  async readdir(path: string): Promise<string[]> {
@@ -1,6 +1,30 @@
 // DO NOT EXPOSE THIS VARIABLE TO PUBLIC, IT IS USED INTERNALLY FOR CLOUDFLARE WORKER
 export const INTERNAL_ENV: Record<string, string> = {};

+/**
+ * Set environment variables before using llamaindex, because some LLM need to access API key before running.
+ *
+ * You have to set the environment variables in Cloudflare Worker environment,
+ * because it doesn't have any global environment variables.
+ *
+ * @example
+ * ```ts
+ * export default {
+ *   async fetch(
+ *     request: Request,
+ *     env: Env,
+ *     ctx: ExecutionContext,
+ *   ): Promise<Response> {
+ *     const { setEnvs } = await import("@llamaindex/env");
+ *     setEnvs(env);
+ *     // ...
+ *     return new Response("Hello, World!");
+ *   },
+ * };
+ * ```
+ *
+ * @param envs Environment variables
+ */
 export function setEnvs(envs: object): void {
  Object.assign(INTERNAL_ENV, envs);
 }
@@ -1,5 +1,23 @@
 # @llamaindex/experimental

+## 0.0.23
+
+### Patch Changes
+
+- Updated dependencies [efa326a]
+  - llamaindex@0.3.6
+
+## 0.0.22
+
+### Patch Changes
+
+- Updated dependencies [bc7a11c]
+- Updated dependencies [2fe2b81]
+- Updated dependencies [5596e31]
+- Updated dependencies [e74fe88]
+- Updated dependencies [be5df5b]
+  - llamaindex@0.3.5
+
 ## 0.0.21

 ### Patch Changes
@@ -1,7 +1,7 @@
 {
  "name": "@llamaindex/experimental",
  "description": "Experimental package for LlamaIndexTS",
-  "version": "0.0.21",
+  "version": "0.0.23",
  "type": "module",
  "types": "dist/type/index.d.ts",
  "main": "dist/cjs/index.js",
@@ -271,9 +271,6 @@ importers:
      notion-md-crawler:
        specifier: ^1.0.0
        version: 1.0.0(encoding@0.1.13)
-      ollama:
-        specifier: ^0.5.0
-        version: 0.5.0
      openai:
        specifier: ^4.38.0
        version: 4.38.1(encoding@0.1.13)
@@ -567,9 +564,6 @@ importers:
      notion-md-crawler:
        specifier: ^1.0.0
        version: 1.0.0(encoding@0.1.13)
-      ollama:
-        specifier: ^0.5.0
-        version: 0.5.0
      openai:
        specifier: ^4.38.0
        version: 4.38.1(encoding@0.1.13)
@@ -634,9 +628,6 @@ importers:
      '@types/node':
        specifier: ^20.12.7
        version: 20.12.7
-      lodash:
-        specifier: ^4.17.21
-        version: 4.17.21
    devDependencies:
      '@aws-crypto/sha256-js':
        specifier: ^5.2.0
@@ -7118,9 +7109,6 @@ packages:
  obuf@1.1.2:
    resolution: {integrity: sha512-PX1wu0AmAdPqOL1mWhqmlOd8kOIZQwGZw6rh7uby9fTc5lhaOWFLX3I6R1hrF9k3zUY40e6igsLGkDXK92LJNg==}

-  ollama@0.5.0:
-    resolution: {integrity: sha512-CRtRzsho210EGdK52GrUMohA2pU+7NbgEaBG3DcYeRmvQthDO7E2LHOkLlUUeaYUlNmEd8icbjC02ug9meSYnw==}
-
  on-finished@2.4.1:
    resolution: {integrity: sha512-oVlzkg3ENAhCk2zdv7IJwd/QUD4z2RxRwpkcGY8psCVcCYZNq4wYnVWALHM+brtuJjePWiYF/ClmuDr8Ch5+kg==}
    engines: {node: '>= 0.8'}
@@ -17688,10 +17676,6 @@ snapshots:

  obuf@1.1.2: {}

-  ollama@0.5.0:
-    dependencies:
-      whatwg-fetch: 3.6.20
-
  on-finished@2.4.1:
    dependencies:
      ee-first: 1.1.1
@@ -26,7 +26,10 @@ if (minorVersion !== expectedMinorVersion) {
  process.exit(1);
 }

-const packages = ["core", "env"];
+const packages = ["env", "core"];
+const envPackageJson = JSON.parse(
+  fs.readFileSync("./packages/env/package.json", "utf8"),
+);
 for (const pkg of packages) {
  const packageJson = JSON.parse(
    fs.readFileSync(`./packages/${pkg}/package.json`, "utf8"),
@@ -36,6 +39,10 @@ for (const pkg of packages) {
  );

  jsrJson.version = packageJson.version;
+  if (pkg === "core") {
+    jsrJson.imports["@llamaindex/env"] =
+      `jsr:@llamaindex/env@${envPackageJson.version}`;
+  }

  fs.writeFileSync(
    `./packages/${pkg}/jsr.json`,
@@ -35,6 +35,9 @@
    {
      "path": "./packages/core/e2e/examples/nextjs-edge-runtime/tsconfig.json"
    },
+    {
+      "path": "./packages/core/e2e/examples/waku-query-engine/tsconfig.json"
+    },
    {
      "path": "./packages/core/tests/tsconfig.json"
    },
Author	SHA1	Message	Date
github-actions[bot]	456d3fb0b3	Release 0.3.6 (#810 ) Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>	2024-05-05 18:40:58 -05:00
Alex Yang	efa326a871	chore: update package.json and usage of lodash (#809 )	2024-05-05 18:30:46 -05:00
Alex Yang	5765b637ce	build: fix jsr release	2024-05-03 18:21:08 -05:00
github-actions[bot]	72687b4f69	Release 0.3.5 (#805 ) Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>	2024-05-03 18:16:39 -05:00
Alex Yang	0c67e1f8f3	build: fix new version script	2024-05-03 18:13:24 -05:00
Alex Yang	4a0619758a	chore: fix jsr.json	2024-05-03 18:09:05 -05:00
Alex Yang	bc7a11cdbe	fix: inline ollama build (#807 )	2024-05-03 18:03:23 -05:00
Alex Yang	5596e31947	feat: improve `@llamaindex/env` (#787 )	2024-05-03 18:03:14 -05:00
Alex Yang	2fe2b813ba	fix: filter with multiple filters in ChromaDB (#784 )	2024-05-03 17:07:45 -05:00
Alex Yang	be5df5b01b	fix(core): multple chat on anthropic agent (#799 )	2024-05-03 16:18:46 -05:00
JT-Dev-215	e74fe88342	fix: change <-> to <=> in the SELECT query (#804 ) Co-authored-by: Alex Yang <himself65@outlook.com>	2024-05-03 12:10:36 -05:00