improve error handling

README.md

@@ -87,13 +87,18 @@ parser = LlamaParse(
     language="en",  # Optionally you can define a language, default=en
 )
 
-with open("./my_file1.pdf", "rb") as f:
-    documents = parser.load_data(f)
+file_name = "my_file1.pdf"
+extra_info = {"file_name": file_name}
+
+with open(f"./{file_name}", "rb") as f:
+    # must provide extra_info with file_name key with passing file object
+    documents = parser.load_data(f, extra_info=extra_info)
 
 # you can also pass file bytes directly
-with open("./my_file1.pdf", "rb") as f:
+with open(f"./{file_name}", "rb") as f:
     file_bytes = f.read()
-    documents = parser.load_data(file_bytes)
+    # must provide extra_info with file_name key with passing file bytes
+    documents = parser.load_data(file_bytes, extra_info=extra_info)
 ```
 
 ## Using with `SimpleDirectoryReader`

examples/multimodal/multimodal_rag_slide_deck.ipynb

@@ -165,7 +165,18 @@
    "execution_count": null,
    "id": "ef82a985-4088-4bb7-9a21-0318e1b9207d",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Parsing text...\n",
+      "Started parsing the file under job_id 62f157a9-9ef9-4e5b-95ac-67093fa25800\n",
+      "..........Parsing PDF file...\n",
+      "Started parsing the file under job_id 1ddd5654-062b-4e19-b488-d66efc9c509d\n"
+     ]
+    }
+   ],
    "source": [
     "print(f\"Parsing text...\")\n",
     "docs_text = parser_text.load_data(\"data/conocophillips.pdf\")\n",
@@ -174,42 +185,36 @@
     "md_json_list = md_json_objs[0][\"pages\"]"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "7506b603-c01f-45de-b354-4a0728dde03c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "print(docs_text[0].get_content())"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
    "id": "5318fb7b-fe6a-4a8a-b82e-4ed7b4512c37",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "print(md_json_list[10][\"md\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "7a46a73e-c6e2-4b0b-bd10-31b0d3e4b70f",
-   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "dict_keys(['page', 'text', 'md', 'images', 'items'])\n"
+      "# Commitment to Disciplined Reinvestment Rate\n",
+      "\n",
+      "| Period       | Description                          | Reinvestment Rate | WTI Average |\n",
+      "|--------------|--------------------------------------|-------------------|-------------|\n",
+      "| 2012-2016    | Industry Growth Focus                | >100%             | ~$75/BBL    |\n",
+      "| 2017-2022    | ConocoPhillips Strategy Reset        | <60%              | ~$63/BBL    |\n",
+      "| 2023E        |                                      |                   | at $80/BBL  |\n",
+      "| 2024-2028    | Disciplined Reinvestment Rate        | ~50%              | at $60/BBL  |\n",
+      "| 2029-2032    |                                      | ~6% CFO CAGR      | at $60/BBL  |\n",
+      "\n",
+      "- **Historic Reinvestment Rate**: Gray bars\n",
+      "- **Reinvestment Rate at $60/BBL WTI**: Blue bars\n",
+      "- **Reinvestment Rate at $80/BBL WTI**: Dashed blue lines\n",
+      "\n",
+      "Reinvestment rate and cash from operations (CFO) are non-GAAP measures. Definitions and reconciliations are included in the Appendix.\n"
      ]
     }
    ],
    "source": [
-    "print(md_json_list[1].keys())"
+    "print(md_json_list[10][\"md\"])"
    ]
   },
   {
@@ -299,7 +304,7 @@
     "    image_files = _get_sorted_image_files(image_dir) if image_dir is not None else None\n",
     "    md_texts = [d[\"md\"] for d in json_dicts] if json_dicts is not None else None\n",
     "\n",
-    "    doc_chunks = docs[0].text.split(\"---\")\n",
+    "    doc_chunks = [c for d in docs for c in d.text.split(\"---\")]\n",
     "    for idx, doc_chunk in enumerate(doc_chunks):\n",
     "        chunk_metadata = {\"page_num\": idx + 1}\n",
     "        if image_files is not None:\n",
@@ -339,25 +344,23 @@
      "output_type": "stream",
      "text": [
       "page_num: 11\n",
-      "image_path: data_images/d9137e19-3974-4b5d-998f-dac0cf29dd9d-page-10.jpg\n",
+      "image_path: data_images/1ddd5654-062b-4e19-b488-d66efc9c509d-page_39.jpg\n",
       "parsed_text_markdown: # Commitment to Disciplined Reinvestment Rate\n",
       "\n",
-      "| Year       | Reinvestment Rate | WTI Average Price | Reinvestment Rate at $60/BBL WTI | Reinvestment Rate at $80/BBL WTI |\n",
-      "|------------|-------------------|-------------------|----------------------------------|----------------------------------|\n",
-      "| 2012-2016  | >100%             | ~$75/BBL          |                                  |                                  |\n",
-      "| 2017-2022  | <60%              | ~$63/BBL          |                                  |                                  |\n",
-      "| 2023E      |                   |                   |                                  | at $80/BBL WTI                   |\n",
-      "| 2024-2028  |                   |                   | at $60/BBL WTI                   | at $80/BBL WTI                   |\n",
-      "| 2029-2032  |                   |                   | at $60/BBL WTI                   | at $80/BBL WTI                   |\n",
+      "| Period       | Description                          | Reinvestment Rate | WTI Average |\n",
+      "|--------------|--------------------------------------|-------------------|-------------|\n",
+      "| 2012-2016    | Industry Growth Focus                | >100%             | ~$75/BBL    |\n",
+      "| 2017-2022    | ConocoPhillips Strategy Reset        | <60%              | ~$63/BBL    |\n",
+      "| 2023E        |                                      |                   | at $80/BBL  |\n",
+      "| 2024-2028    | Disciplined Reinvestment Rate        | ~50%              | at $60/BBL  |\n",
+      "| 2029-2032    |                                      | ~6% CFO CAGR      | at $60/BBL  |\n",
       "\n",
-      "**Disciplined Reinvestment Rate is the Foundation for Superior Returns on and of Capital, while Driving Durable CFO Growth**\n",
+      "- **Historic Reinvestment Rate**: Gray bars\n",
+      "- **Reinvestment Rate at $60/BBL WTI**: Blue bars\n",
+      "- **Reinvestment Rate at $80/BBL WTI**: Dashed blue lines\n",
       "\n",
-      "- ~50% 10-Year Reinvestment Rate\n",
-      "- ~6% CFO CAGR 2024-2032 at $60/BBL WTI Mid-Cycle Planning Price\n",
-      "\n",
-      "**Note:** Reinvestment rate and cash from operations (CFO) are non-GAAP measures. Definitions and reconciliations are included in the Appendix.\n",
-      "parsed_text: \n",
-      "Commitment to Disciplined Reinvestment Rate\n",
+      "Reinvestment rate and cash from operations (CFO) are non-GAAP measures. Definitions and reconciliations are included in the Appendix.\n",
+      "parsed_text: Commitment to Disciplined Reinvestment Rate\n",
       "                         Industry                    ConocoPhillips\n",
       "                                                     Strategy Reset                   Disciplined Reinvestment Rate is the Foundation for Superior\n",
       "                      Growth Focus                                                    Returns on and of Capital, while Driving Durable CFO Growth\n",
@@ -374,7 +377,7 @@
       "          0%\n",
       "                          2012-2016                        2017-2022                         2023E                          2024-2028                       2029-2032\n",
       "                                    Historic Reinvestment Rate            Reinvestment Rate at $60/BBL WTI                 Reinvestment Rate at $80/BBL WTI\n",
-      " Reinvestment rate andcashfrom operations (CFO) are non-GAAP measures: Definitions and reconciliations are included in the Appendix                                    ConocoPhillips\n"
+      " Reinvestment rate and cash from operations (CFO) are non-GAAP measures: Definitions and reconciliations are included in the Appendix                                  ConocoPhillips\n"
      ]
     }
    ],
@@ -397,7 +400,17 @@
    "execution_count": null,
    "id": "6ea53c31-0e38-421c-8d9b-0e3adaa1677e",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/jerryliu/Programming/gpt_index/.venv/lib/python3.10/site-packages/tiktoken/core.py:50: RuntimeWarning: coroutine 'LlamaParse.aload_data' was never awaited\n",
+      "  self._core_bpe = _tiktoken.CoreBPE(mergeable_ranks, special_tokens, pat_str)\n",
+      "RuntimeWarning: Enable tracemalloc to get the object allocation traceback\n"
+     ]
+    }
+   ],
    "source": [
     "import os\n",
     "from llama_index.core import (\n",
@@ -588,7 +601,7 @@
       "                            Under $40/BBL Cost of Supply                              10-Year Plan Cumulative Production (BBOE)\n",
       "      S50                   S32/BBL                                                Lower 48                           Alaska\n",
       "                    Average Cost of Supply\n",
-      "  3$40                                                                                                                        GKA        GWA\n",
+      "  3 $40                                                                                                                       GKA        GWA\n",
       "                                                                                                                      GPA     WNS\n",
       "      $30                                                                                                             EMENA\n",
       "  3                                                                                                                              Norway\n",
@@ -599,7 +612,7 @@
       "                                                                                                                      APLNG        Montney\n",
       "       S0\n",
       "                                               10              15              20                         Bakken\n",
-      "                                         Resource (BBOE)                           Eagle Ford             Other       MalaysiaChina Surmont\n",
+      "                                         Resource (BBOE)                           Eagle Ford             Other       Malaysia ChinaSurmont\n",
       "                 Lower 48      Canada       Alaska      EMENA    Asia Pacific\n",
       "Costs assumemid-cycle price environment of S60/BBL WTI:\n",
       "                                                                                                                                           ConocoPhillips\n"
@@ -687,70 +700,126 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "1cdce5d8-6bb3-4cd3-929d-1cec249d9052",
+   "id": "d78e53cf-35cb-4ef8-b03e-1b47ba15ae64",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Added user message to memory: How does the Conoco Phillips capex/EUR in the delaware basin compare against other competitors?\n",
+      "Added user message to memory: Tell me about the diverse geographies where Conoco Phillips has a production base\n",
       "=== Calling Function ===\n",
-      "Calling function: vector_tool with args: {\"input\": \"Conoco Phillips capex/EUR in the Delaware Basin\"}\n",
+      "Calling function: vector_tool with args: {\"input\": \"Conoco Phillips production base geographies\"}\n",
       "=== Function Output ===\n",
-      "The ConocoPhillips capex/EUR in the Delaware Basin is $10/BOE.\n",
+      "ConocoPhillips' production base geographies include:\n",
       "\n",
-      "I obtained this information from the image provided. The image clearly shows a bar chart under the section \"Delaware Basin Well Capex/EUR ($/BOE)\" where ConocoPhillips is listed with a capex/EUR of $10/BOE. This information is consistent with the parsed markdown text, which also lists ConocoPhillips' capex/EUR as $10/BOE in the Delaware Basin. There are no discrepancies between the image and the parsed markdown text in this case.\n",
-      "=== Calling Function ===\n",
-      "Calling function: vector_tool with args: {\"input\": \"competitors capex/EUR in the Delaware Basin\"}\n",
-      "=== Function Output ===\n",
-      "The competitors' Capex/EUR in the Delaware Basin can be found in the image on the slide titled \"Delaware: Vast Inventory with Proven Track Record of Performance.\" The relevant information is presented in a bar chart under the section \"Delaware Basin Well Capex/EUR ($/BOE)\".\n",
+      "1. **Lower 48** (Permian, Eagle Ford, Bakken, Other)\n",
+      "2. **Alaska** (GKA, GWA, GPA, WNS)\n",
+      "3. **EMENA** (Norway, Libya, Qatar)\n",
+      "4. **Asia Pacific** (APLNG, Malaysia, China)\n",
+      "5. **Canada** (Montney, Surmont)\n",
       "\n",
-      "Here are the details:\n",
-      "\n",
-      "- ConocoPhillips: $10/BOE\n",
-      "- Competitor 1: $15/BOE\n",
-      "- Competitor 2: $20/BOE\n",
-      "- Competitor 3: $25/BOE\n",
-      "- Competitor 4: $30/BOE\n",
-      "- Competitor 5: $35/BOE\n",
-      "- Competitor 6: $40/BOE\n",
-      "- Competitor 7: $45/BOE\n",
-      "\n",
-      "This information was obtained directly from the image, which provides a clear visual representation of the Capex/EUR values for ConocoPhillips and its competitors in the Delaware Basin. The parsed markdown text also confirms these values, ensuring consistency between the image and the text.\n",
+      "This information was derived from the image on page 14, which provides a detailed breakdown of the diverse production base and the regions involved. The parsed markdown and raw text also support this information, but the image provides the clearest and most comprehensive view. There are no discrepancies between the image and the parsed text in this case.\n",
       "=== LLM Response ===\n",
-      "The capital expenditure per estimated ultimate recovery (capex/EUR) for ConocoPhillips in the Delaware Basin is $10 per barrel of oil equivalent (BOE). When compared to its competitors, ConocoPhillips has a significantly lower capex/EUR. Here are the capex/EUR values for ConocoPhillips and its competitors:\n",
+      "ConocoPhillips has a diverse production base spread across various geographies, including:\n",
       "\n",
-      "- **ConocoPhillips**: $10/BOE\n",
-      "- **Competitor 1**: $15/BOE\n",
-      "- **Competitor 2**: $20/BOE\n",
-      "- **Competitor 3**: $25/BOE\n",
-      "- **Competitor 4**: $30/BOE\n",
-      "- **Competitor 5**: $35/BOE\n",
-      "- **Competitor 6**: $40/BOE\n",
-      "- **Competitor 7**: $45/BOE\n",
+      "1. **Lower 48**:\n",
+      "   - Permian Basin\n",
+      "   - Eagle Ford\n",
+      "   - Bakken\n",
+      "   - Other regions within the continental United States\n",
       "\n",
-      "This data indicates that ConocoPhillips has a more cost-efficient operation in the Delaware Basin compared to its competitors.\n",
-      "The capital expenditure per estimated ultimate recovery (capex/EUR) for ConocoPhillips in the Delaware Basin is $10 per barrel of oil equivalent (BOE). When compared to its competitors, ConocoPhillips has a significantly lower capex/EUR. Here are the capex/EUR values for ConocoPhillips and its competitors:\n",
+      "2. **Alaska**:\n",
+      "   - Greater Kuparuk Area (GKA)\n",
+      "   - Greater Prudhoe Area (GPA)\n",
+      "   - Greater Willow Area (GWA)\n",
+      "   - Western North Slope (WNS)\n",
       "\n",
-      "- **ConocoPhillips**: $10/BOE\n",
-      "- **Competitor 1**: $15/BOE\n",
-      "- **Competitor 2**: $20/BOE\n",
-      "- **Competitor 3**: $25/BOE\n",
-      "- **Competitor 4**: $30/BOE\n",
-      "- **Competitor 5**: $35/BOE\n",
-      "- **Competitor 6**: $40/BOE\n",
-      "- **Competitor 7**: $45/BOE\n",
+      "3. **EMENA (Europe, Middle East, and North Africa)**:\n",
+      "   - Norway\n",
+      "   - Libya\n",
+      "   - Qatar\n",
       "\n",
-      "This data indicates that ConocoPhillips has a more cost-efficient operation in the Delaware Basin compared to its competitors.\n"
+      "4. **Asia Pacific**:\n",
+      "   - Australia Pacific LNG (APLNG)\n",
+      "   - Malaysia\n",
+      "   - China\n",
+      "\n",
+      "5. **Canada**:\n",
+      "   - Montney\n",
+      "   - Surmont\n",
+      "\n",
+      "These regions highlight the global reach and diverse geographical footprint of ConocoPhillips' production operations.\n",
+      "Added user message to memory: Tell me about the diverse geographies where Conoco Phillips has a production base\n",
+      "=== Calling Function ===\n",
+      "Calling function: vector_tool with args: {\"input\": \"diverse geographies where Conoco Phillips has a production base\"}\n",
+      "=== Function Output ===\n",
+      "ConocoPhillips has a diverse production base that includes the Lower 48 (Permian, Bakken, Eagle Ford), Alaska, Canada (Montney, Surmont), EMENA (Norway, Libya), Asia Pacific (Malaysia, China, APLNG), and Qatar.\n",
+      "=== LLM Response ===\n",
+      "ConocoPhillips has a diverse production base spanning several key geographies:\n",
+      "\n",
+      "1. **Lower 48 (United States)**: This includes major production areas such as the Permian Basin, Bakken Formation, and Eagle Ford Shale.\n",
+      "2. **Alaska**: Significant operations in the North Slope region.\n",
+      "3. **Canada**: Operations in the Montney Formation and the Surmont oil sands project.\n",
+      "4. **EMENA (Europe, Middle East, and North Africa)**: Notable operations in Norway and Libya.\n",
+      "5. **Asia Pacific**: Includes operations in Malaysia, China, and the Australia Pacific LNG (APLNG) project.\n",
+      "6. **Qatar**: Involvement in the country's energy sector.\n",
+      "\n",
+      "These regions highlight the company's extensive and varied geographical footprint in the energy production industry.\n"
      ]
     }
    ],
    "source": [
-    "# response = agent.query(\"Tell me about the different regions and subregions where Conoco Phillips has a production base.\")\n",
-    "response = agent.query(\n",
-    "    \"How does the Conoco Phillips capex/EUR in the delaware basin compare against other competitors?\"\n",
+    "query = (\n",
+    "    \"Tell me about the diverse geographies where Conoco Phillips has a production base\"\n",
     ")\n",
+    "response = agent.query(query)\n",
+    "base_response = base_agent.query(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "355d2aa4-c26f-480e-b512-4446acbd9227",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ConocoPhillips has a diverse production base spread across various geographies, including:\n",
+      "\n",
+      "1. **Lower 48**:\n",
+      "   - Permian Basin\n",
+      "   - Eagle Ford\n",
+      "   - Bakken\n",
+      "   - Other regions within the continental United States\n",
+      "\n",
+      "2. **Alaska**:\n",
+      "   - Greater Kuparuk Area (GKA)\n",
+      "   - Greater Prudhoe Area (GPA)\n",
+      "   - Greater Willow Area (GWA)\n",
+      "   - Western North Slope (WNS)\n",
+      "\n",
+      "3. **EMENA (Europe, Middle East, and North Africa)**:\n",
+      "   - Norway\n",
+      "   - Libya\n",
+      "   - Qatar\n",
+      "\n",
+      "4. **Asia Pacific**:\n",
+      "   - Australia Pacific LNG (APLNG)\n",
+      "   - Malaysia\n",
+      "   - China\n",
+      "\n",
+      "5. **Canada**:\n",
+      "   - Montney\n",
+      "   - Surmont\n",
+      "\n",
+      "These regions highlight the global reach and diverse geographical footprint of ConocoPhillips' production operations.\n"
+     ]
+    }
+   ],
+   "source": [
     "print(str(response))"
    ]
   },
@@ -764,85 +833,82 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "page_num: 38\n",
-      "image_path: data_images/d9137e19-3974-4b5d-998f-dac0cf29dd9d-page-37.jpg\n",
-      "parsed_text_markdown: # Delaware: Vast Inventory with Proven Track Record of Performance\n",
+      "page_num: 14\n",
+      "image_path: data_images/1ddd5654-062b-4e19-b488-d66efc9c509d-page_12.jpg\n",
+      "parsed_text_markdown: # Our Differentiated Portfolio: Deep, Durable and Diverse\n",
       "\n",
-      "## Prolific Acreage Spanning Over ~659,000 Net Acres¹\n",
+      "## ~20 BBOE of Resource\n",
+      "Under $40/BBL Cost of Supply\n",
       "\n",
-      "![Map of Delaware Basin](image)\n",
+      "### ~ $32/BBL\n",
+      "Average Cost of Supply\n",
       "\n",
-      "### Total 10-Year Operated Permian Inventory\n",
+      "### WTI Cost of Supply ($/BBL)\n",
       "\n",
-      "- Delaware Basin: 65%\n",
-      "- Midland Basin: 35%\n",
+      "| Cost ($/BBL) | Resource (BBOE) |\n",
+      "|--------------|-----------------|\n",
+      "| $0           | 0               |\n",
+      "| $10          |                 |\n",
+      "| $20          |                 |\n",
+      "| $30          |                 |\n",
+      "| $40          |                 |\n",
+      "| $50          |                 |\n",
       "\n",
-      "### High Single-Digit Production Growth\n",
+      "- **Legend:**\n",
+      "  - Lower 48\n",
+      "  - Canada\n",
+      "  - Alaska\n",
+      "  - EMENA\n",
+      "  - Asia Pacific\n",
       "\n",
-      "## 12-Month Cumulative Production³ (BOE/FT)\n",
+      "*Costs assume a mid-cycle price environment of $60/BBL WTI.*\n",
       "\n",
-      "| Months | 2019 | 2020 | 2021 | 2022 |\n",
-      "|--------|------|------|------|------|\n",
-      "| 1      | 0    | 0    | 0    | 0    |\n",
-      "| 2      | 5    | 6    | 7    | 8    |\n",
-      "| 3      | 10   | 12   | 14   | 16   |\n",
-      "| 4      | 15   | 18   | 21   | 24   |\n",
-      "| 5      | 20   | 24   | 28   | 32   |\n",
-      "| 6      | 25   | 30   | 35   | 40   |\n",
-      "| 7      | 30   | 36   | 42   | 48   |\n",
-      "| 8      | 35   | 42   | 49   | 56   |\n",
-      "| 9      | 40   | 48   | 56   | 64   |\n",
-      "| 10     | 45   | 54   | 63   | 72   |\n",
-      "| 11     | 50   | 60   | 70   | 80   |\n",
-      "| 12     | 55   | 66   | 77   | 88   |\n",
+      "## Diverse Production Base\n",
+      "10-Year Plan Cumulative Production (BBOE)\n",
       "\n",
-      "~30% Improved Performance from 2019 to 2022\n",
-      "\n",
-      "## Delaware Basin Well Capex/EUR⁴ ($/BOE)\n",
-      "\n",
-      "| Company          | Capex/EUR |\n",
-      "|------------------|-----------|\n",
-      "| ConocoPhillips   | 10        |\n",
-      "| Competitor 1     | 15        |\n",
-      "| Competitor 2     | 20        |\n",
-      "| Competitor 3     | 25        |\n",
-      "| Competitor 4     | 30        |\n",
-      "| Competitor 5     | 35        |\n",
-      "| Competitor 6     | 40        |\n",
-      "| Competitor 7     | 45        |\n",
-      "\n",
-      "---\n",
-      "\n",
-      "¹ Unconventional acres.  \n",
-      "² Source: Enverus and ConocoPhillips (March 2023).  \n",
-      "³ Source: Enverus (March 2023) based on wells online year.  \n",
-      "⁴ Source: Enverus (March 2023). Average single well capex/EUR. Top eight public operators based on wells online in years 2021-2022, greater than 50% oil weight. COP based on COP well design. Competitors include: CVX, DVN, EOG, MTDR, OXY, PR and XOM.\n",
-      "parsed_text: \n",
-      "Delaware: Vast Inventory with Proven Track Record of Performance\n",
-      "        New                       Prolific Acreage Spanning Over                                                        12-Month Cumulative Production? (BOE/FT)\n",
-      "       Mexico                                 659,000 Net Acres'                                             40\n",
-      "                       Texas                                                                                                                                                                       3828\n",
-      "                                                                                                             30                                                                                    2019\n",
-      "                                                                                                             20                                                                            30%\n",
-      "                                                                                                             10                                                         Improved Performancefrom 2019 to 2022\n",
-      "           Total\n",
-      "   Permian Inventory\n",
-      "                    10-Year Operated\n",
-      "                                                                                                                            2                                                      10     11     12\n",
-      "                                                                                                                                                        Months\n",
-      "                                                                                                                         Delaware Basin Well Capex/EUR4 (S/BOE)\n",
-      "                      65%                                                                                     25\n",
-      "          Delaware Basin                                                                                      20\n",
-      "          Midland Basin                                                                                       15\n",
-      "                                              Low         HighCost of Supplyz                                 10  ConocoPhillips\n",
-      "     High Single-Digit Production Growth\n",
-      " \"Unconventional acres. 2Source: Enverus and ConocoPhillips (March 2023). 3SourceEnverus (March 2023) based on wells online year: \"Source; Enverus (March 2023). Average single well capex/EUR Top eight public operators based on\n",
-      "wells online in years 2021-2022, greater than 50% oil weight; COP based on COP well design: Competitors include; CVX DVN, EOG; MTDR, OXY, PR and XOM:                                     ConocoPhillips\n"
+      "| Region       | Sub-region      |\n",
+      "|--------------|-----------------|\n",
+      "| Lower 48     | Permian         |\n",
+      "|              | Eagle Ford      |\n",
+      "|              | Bakken          |\n",
+      "|              | Other           |\n",
+      "| Alaska       | GKA             |\n",
+      "|              | GWA             |\n",
+      "|              | GPA             |\n",
+      "|              | WNS             |\n",
+      "| EMENA        | Norway          |\n",
+      "|              | Libya           |\n",
+      "|              | Qatar           |\n",
+      "| Asia Pacific | APLNG           |\n",
+      "|              | Malaysia        |\n",
+      "|              | China           |\n",
+      "| Canada       | Montney         |\n",
+      "|              | Surmont         |\n",
+      "parsed_text: Our Differentiated Portfolio: Deep; Durable and Diverse\n",
+      "                              20 BBOE of Resource                                           Diverse Production Base\n",
+      "                            Under $40/BBL Cost of Supply                              10-Year Plan Cumulative Production (BBOE)\n",
+      "      S50                   S32/BBL                                                Lower 48                           Alaska\n",
+      "                    Average Cost of Supply\n",
+      "  3 $40                                                                                                                       GKA        GWA\n",
+      "                                                                                                                      GPA     WNS\n",
+      "      $30                                                                                                             EMENA\n",
+      "  3                                                                                                                              Norway\n",
+      "  8   $20\n",
+      "  E                                                                                                                   Qatar      Libya\n",
+      "                                                                                                                      Asia Pacific Canada\n",
+      "      $10                                                                          Permian\n",
+      "                                                                                                                      APLNG        Montney\n",
+      "       S0\n",
+      "                                               10              15              20                         Bakken\n",
+      "                                         Resource (BBOE)                           Eagle Ford             Other       Malaysia ChinaSurmont\n",
+      "                 Lower 48      Canada       Alaska      EMENA    Asia Pacific\n",
+      "Costs assumemid-cycle price environment of S60/BBL WTI:\n",
+      "                                                                                                                                           ConocoPhillips\n"
      ]
     }
    ],
    "source": [
-    "print(response.source_nodes[0].get_content(metadata_mode=\"all\"))"
+    "print(response.source_nodes[7].get_content(metadata_mode=\"all\"))"
    ]
   },
   {
@@ -855,26 +921,20 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Added user message to memory: How does the Conoco Phillips capex/EUR in the delaware basin compare against other competitors?\n",
-      "=== Calling Function ===\n",
-      "Calling function: vector_tool with args: {\"input\": \"Conoco Phillips capex/EUR in the Delaware Basin\"}\n",
-      "=== Function Output ===\n",
-      "ConocoPhillips' capex/EUR in the Delaware Basin is approximately $20/BOE.\n",
-      "=== Calling Function ===\n",
-      "Calling function: vector_tool with args: {\"input\": \"competitors capex/EUR in the Delaware Basin\"}\n",
-      "=== Function Output ===\n",
-      "The average single well capex/EUR for competitors in the Delaware Basin is between $10 and $25 per BOE.\n",
-      "=== LLM Response ===\n",
-      "ConocoPhillips' capex/EUR in the Delaware Basin is approximately $20 per BOE. In comparison, the average capex/EUR for competitors in the Delaware Basin ranges between $10 and $25 per BOE. This places ConocoPhillips' capex/EUR towards the higher end of the competitive range.\n",
-      "ConocoPhillips' capex/EUR in the Delaware Basin is approximately $20 per BOE. In comparison, the average capex/EUR for competitors in the Delaware Basin ranges between $10 and $25 per BOE. This places ConocoPhillips' capex/EUR towards the higher end of the competitive range.\n"
+      "ConocoPhillips has a diverse production base spanning several key geographies:\n",
+      "\n",
+      "1. **Lower 48 (United States)**: This includes major production areas such as the Permian Basin, Bakken Formation, and Eagle Ford Shale.\n",
+      "2. **Alaska**: Significant operations in the North Slope region.\n",
+      "3. **Canada**: Operations in the Montney Formation and the Surmont oil sands project.\n",
+      "4. **EMENA (Europe, Middle East, and North Africa)**: Notable operations in Norway and Libya.\n",
+      "5. **Asia Pacific**: Includes operations in Malaysia, China, and the Australia Pacific LNG (APLNG) project.\n",
+      "6. **Qatar**: Involvement in the country's energy sector.\n",
+      "\n",
+      "These regions highlight the company's extensive and varied geographical footprint in the energy production industry.\n"
      ]
     }
    ],
    "source": [
-    "# base_response = base_agent.query(\"Tell me about the different regions and subregions where Conoco Phillips has a production base.\")\n",
-    "base_response = base_agent.query(\n",
-    "    \"How does the Conoco Phillips capex/EUR in the delaware basin compare against other competitors?\"\n",
-    ")\n",
     "print(str(base_response))"
    ]
   },
@@ -888,30 +948,31 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Deep, Durable and Diverse Portfolio with Significant Growth Runway\n",
-      "    1,2002022 Lower 48 Unconventional Production' (MBOED                                                  S50     ~S32/BBL\n",
-      "     000 ConocoPhillips                                                                                                   Cost of SupplyAverage\n",
-      "       00                                                                                                 S40\n",
-      "      500                                                                                            3\n",
-      "      400                                                                                            1    S30\n",
-      "     200\n",
-      "                                                                                                      5\n",
-      "   15,000ConocoPhillipsNet Remaining Well Inventory?                                                  1   S20\n",
-      "   12,000                                                                                                 S10\n",
-      "      000\n",
-      "      0o0                                                                                                  SO\n",
-      "     3,000                                                                                                                                                                         10\n",
-      "                                                                                                                                                Resource (BBOE)\n",
-      "                                                                                                                    Delaware Basin      Midland Basin      Eagle Ford       Bakken        Other\n",
-      "                        Largest Lower 48 Unconventional Producer; Growing into the Next Decade\n",
-      " onshore operated inventory that achieves 15% IRR at $SO/BBL WTI, Competitors include CVX, DVN, EOG, FANG, MRO, OXY, PXD,and XOM:\n",
-      "                                                                                                                                 Source: Wood Mackenzie Lower 48 Unconventional Plays 2022 ProductionCompetitors include CVX, DVN; EOG, FANG, MRO, OXY, PXD and XOM; greaterthan50% liquids weight: ?Source: Wood Mackenzie (March 2023), Lower 48\n",
-      "                                                                                                                                                                                  ConocoPhillips\n"
+      "Our Differentiated Portfolio: Deep; Durable and Diverse\n",
+      "                              20 BBOE of Resource                                           Diverse Production Base\n",
+      "                            Under $40/BBL Cost of Supply                              10-Year Plan Cumulative Production (BBOE)\n",
+      "      S50                   S32/BBL                                                Lower 48                           Alaska\n",
+      "                    Average Cost of Supply\n",
+      "  3 $40                                                                                                                       GKA        GWA\n",
+      "                                                                                                                      GPA     WNS\n",
+      "      $30                                                                                                             EMENA\n",
+      "  3                                                                                                                              Norway\n",
+      "  8   $20\n",
+      "  E                                                                                                                   Qatar      Libya\n",
+      "                                                                                                                      Asia Pacific Canada\n",
+      "      $10                                                                          Permian\n",
+      "                                                                                                                      APLNG        Montney\n",
+      "       S0\n",
+      "                                               10              15              20                         Bakken\n",
+      "                                         Resource (BBOE)                           Eagle Ford             Other       Malaysia ChinaSurmont\n",
+      "                 Lower 48      Canada       Alaska      EMENA    Asia Pacific\n",
+      "Costs assumemid-cycle price environment of S60/BBL WTI:\n",
+      "                                                                                                                                           ConocoPhillips\n"
      ]
     }
    ],
    "source": [
-    "print(base_response.source_nodes[0].get_content(metadata_mode=\"llm\"))"
+    "print(base_response.source_nodes[1].get_content(metadata_mode=\"all\"))"
    ]
   }
  ],

llama_parse/base.py

@@ -91,6 +91,10 @@ class LlamaParse(BasePydanticReader):
         default=False,
         description="Note: Non compatible with gpt-4o. If set to true, the parser will use a faster mode to extract text from documents. This mode will skip OCR of images, and table/heading reconstruction.",
     )
+    premium_mode: bool = Field(
+        default=False,
+        description="Use our best parser mode if set to True.",
+    )
     do_not_unroll_columns: Optional[bool] = Field(
         default=False,
         description="If set to true, the parser will keep column in the text according to document layout. Reduce reconstruction accuracy, and LLM's/embedings performances in most case.",
@@ -227,6 +231,7 @@ class LlamaParse(BasePydanticReader):
             "skip_diagonal_text": self.skip_diagonal_text,
             "do_not_cache": self.do_not_cache,
             "fast_mode": self.fast_mode,
+            "premium_mode": self.premium_mode,
             "do_not_unroll_columns": self.do_not_unroll_columns,
             "gpt4o_mode": self.gpt4o_mode,
             "gpt4o_api_key": self.gpt4o_api_key,
@@ -303,7 +308,8 @@ class LlamaParse(BasePydanticReader):
                     continue
 
                 # Allowed values "PENDING", "SUCCESS", "ERROR", "CANCELED"
-                status = result.json()["status"]
+                result_json = result.json()
+                status = result_json["status"]
                 if status == "SUCCESS":
                     parsed_result = await client.get(result_url, headers=headers)
                     return parsed_result.json()
@@ -315,6 +321,14 @@ class LlamaParse(BasePydanticReader):
                         print(".", end="", flush=True)
 
                     await asyncio.sleep(self.check_interval)
+                else:
+                    error_code = result_json.get("error_code", "No error code found")
+                    error_message = result_json.get(
+                        "error_message", "No error message found"
+                    )
+
+                    exception_str = f"Job ID: {job_id} failed with status: {status}, Error code: {error_code}, Error message: {error_message}"
+                    raise Exception(exception_str)
 
     async def _aload_data(
         self,
@@ -416,12 +430,13 @@ class LlamaParse(BasePydanticReader):
             job_id = await self._create_job(file_path, extra_info=extra_info)
             if self.verbose:
                 print("Started parsing the file under job_id %s" % job_id)
-
             result = await self._get_job_result(job_id, "json")
             result["job_id"] = job_id
-            result["file_path"] = file_path
-            return [result]
 
+            if not isinstance(file_path, (bytes, BufferedIOBase)):
+                result["file_path"] = str(file_path)
+
+            return [result]
         except Exception as e:
             file_repr = file_path if isinstance(file_path, str) else "<bytes/buffer>"
             print(f"Error while parsing the file '{file_repr}':", e)
@@ -506,7 +521,9 @@ class LlamaParse(BasePydanticReader):
 
                         image["path"] = image_path
                         image["job_id"] = job_id
-                        image["original_pdf_path"] = result["file_path"]
+
+                        image["original_file_path"] = result.get("file_path", None)
+
                         image["page_number"] = page["page"]
                         with open(image_path, "wb") as f:
                             image_url = f"{self.base_url}/api/parsing/job/{job_id}/result/image/{image_name}"

llama_parse/utils.py

@@ -10,7 +10,6 @@ class ResultType(str, Enum):
 
     TXT = "text"
     MD = "markdown"
-    JSON = "json"
 
 
 class Language(str, Enum):

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "llama-parse"
-version = "0.5.4"
+version = "0.5.7"
 description = "Parse files into RAG-Optimized formats."
 authors = ["Logan Markewich <logan@llamaindex.ai>"]
 license = "MIT"